2020-10-25T20:48:34Zhttp://edoc.mpg.de/ac_p_oai.ploai:edoc.mpg.de:2018042010-12-0387:937
Improved Hardware-Accelerated Visual Hull Rendering
Li, Ming
Magnor, Marcus
Seidel, Hans-Peter
Ertl, Thomas
Girod, Bernd
Greiner, Günther
Niemann, Heinrich
Seidel, Hans-Peter
Steinbach, Eckehard
Westermann, Rüdiger
The visual hull is an efficient shape approximation for the purpose of
reconstructing and visualizing dynamic objects. Recently, rapid progress in
graphics hardware development has made it possible to render visual hulls from
a set of silhouette images in real-time.
In this paper we present several new algorithms to improve the generality and
quality of hardware-accelerated visual hull rendering. First, a multi-pass
approach employs texture objects and the stencil buffer to enable the visual
hull rendering algorithm to deal with arbitrary numbers of input images.
Secondly, flexible programmability of state-of-the-art graphics hardware is
exploited to achieve smooth transitions between textures from different
reference views projected onto visual hulls. In addition, visibility problems
with projective texture mapping are solved by using the shadow mapping
technique. We test our rendering algorithms on various off-the-shelf graphics
cards and achieve real-time frame rates.
Akademische Verlagsgesellschaft Aka
2003
Conference-Paper
http://edoc.mpg.de/201804
urn:ISBN:3-89838-048-3
Vision, Modeling and Visualization 2003 (VMV-03) : proceedings, Akademische Verlagsgesellschaft Aka, 151-158 (2003)
en
oai:edoc.mpg.de:2018052010-12-0387:937
Interactive Rendering of Translucent Objects
Lensch, Hendrik
Goesele, Michael
Bekaert, Philippe
Kautz, Jan
Magnor, Marcus
Lang, Jochen
Seidel, Hans-Peter
This paper presents a rendering method for translucent objects, in which
viewpoint and illumination can be
modified at interactive rates. In a preprocessing step, the impulse response to
incoming light impinging at each
surface point is computed and stored in two different ways: The local effect on
close-by surface points is modeled
as a per-texel filter kernel that is applied to a texture map representing the
incident illumination. The global
response (i.e. light shining through the object) is stored as vertex-to-vertex
throughput factors for the triangle
mesh of the object. During rendering, the illumination map for the object is
computed according to the current
lighting situation and then filtered by the precomputed kernels. The
illumination map is also used to derive the
incident illumination on the vertices which is distributed via the
vertex-to-vertex throughput factors to the other
vertices. The final image is obtained by combining the local and global
response. We demonstrate the performance
of our method for several models.
2003
Article
http://edoc.mpg.de/201805
urn:ISSN:0167-7055
Computer Graphics Forum, v.22, 195-205 (2003)
en
oai:edoc.mpg.de:2018262010-12-0387:937
Online Accelerated Rendering of Visual Hulls in Real Scenes
Li, Ming
Magnor, Marcus
Seidel, Hans-Peter
This paper presents an online system which is capable of reconstructing and
rendering dynamic objects in real scenes. We reconstruct visual hulls of the
objects by using a shape-from-silhouette approach. During rendering, a novel
blending scheme is employed to compose multiple background images. Visibility
artifacts on the dynamic object are removed by using opaque projective texture
mapping. We also propose a dynamic texture packing technique to improve
rendering performance by exploiting region-of-interest information. Our system
takes multiple live or pre-recorded video streams as input. It produces
realistic real-time rendering results of dynamic objects in their surrounding
natural environment in which the user can freely navigate.
2003
Article
http://edoc.mpg.de/201826
urn:ISSN:1213-6972
Journal of WSCG, v.11, 290-297 (2003)
en
oai:edoc.mpg.de:2018472010-12-0387:937
Fast Hologram Synthesis for 3D Geometry Models using Graphics Hardware
Petz, Christoph
Magnor, Marcus
Jeong, Tung H.
Stevenson, Sylvia H.
The holographic visualization of three-dimensional object geometry still
represents a major challenge in computational holography research. Besides the
development of suitable holographic display devices, the fast calculation of the
hologram's interference pattern for complex-shaped three-dimensional objects is
an important pre-requisite of any interactive holographic display system. We
present a fast method for rendering full-parallax holograms using a standard PC
with a consumer-market graphics card. To calculate the hologram of a 3D
object, scaled and translated versions of the interference pattern of simple
primitives, e.g. point sources, are superimposed. The
hologram is built up completely
on-board the graphics card.
To avoid numerical inaccuracies due to limited
frame-buffer resolution, we use a hierarchical approach.
Using an NVidia
Geforce4 graphics card, the proposed
algorithm takes 1.0 second to calculate the 512x512-pixel hologram of 1024
primitives.
SPIE
http://www.mpi-sb.mpg.de/~petz/holography.html
2003
Conference-Paper
http://edoc.mpg.de/201847
urn:ISBN:0-8194-4805-2
Practical Holography XVII and Holographic Materials IX, SPIE, 266-275 (2003)
en
oai:edoc.mpg.de:2018542010-12-0387:937
Real-time, Free-viewpoint Video Rendering from Volumetric Geometry
Goldluecke, Bastian
Magnor, Marcus
Ebrahimi, Touradj
Sikora, Thomas
The aim of this work is to render high-quality views of a dynamic scene
from novel viewpoints in real-time. An online system available at our institute
computes the visual hull as a geometry proxy to guide the rendering at
interactive rates. Because only a sparse set of cameras distributed around the
scene is used to record the scene, only an coarse model of the scene geometry
can be recovered. To alleviate this problem, we render textured billboards
defined by the voxel model of the visual hull, preserving details in the source
images while
achieving excellent performance. By exploiting multi-texturing capabilities of
modern graphics hardware, real-time frame rates are attained. Our algorithm can
be used as part of an inexpensive system to display 3D-videos, or ultimately
even in live 3D-television. The user is able to watch the scene from an
arbitrary viewpoint chosen interactively.
SPIE
2003
Conference-Paper
http://edoc.mpg.de/201854
urn:ISBN:0-8194-5023-5
Visual Communications and Image Processing 2003, SPIE, 1152-1158 (2003)
en
oai:edoc.mpg.de:2018562010-12-0387:937
A Flexible and Versatile Studio for Synchronized Multi-view Video Recording
Theobalt, Christian
Li, Ming
Magnor, Marcus
Seidel, Hans-Peter
Hall, Peter
Willis, Philip
In recent years, the convergence of computer vision and computer graphics has
put forth
new research areas that work on scene reconstruction from and analysis of
multi-view video
footage. In free-viewpoint video, for example, new views of a scene are
generated from an arbitrary viewpoint
in real-time using a set of multi-view video streams as inputs.
The analysis of real-world scenes from multi-view video
to extract motion information or reflection models is another field of research
that
greatly benefits from high-quality input data.
Building a recording setup for multi-view video involves a great effort on the
hardware
as well as the software side. The amount of image data to be processed is huge,
a decent lighting and camera setup is essential for a naturalistic scene
appearance and
robust background subtraction, and the computing infrastructure has to enable
real-time processing of the recorded material.
This paper describes our recording setup for multi-view video acquisition that
enables the
synchronized recording
of dynamic scenes from multiple camera positions under controlled conditions.
The requirements
to the room and their implementation in the separate components of the studio
are described in detail.
The efficiency and flexibility of the room is demonstrated on the basis of the
results
that we obtain with a real-time 3D scene reconstruction system, a system for
non-intrusive optical
motion capture and a model-based free-viewpoint video system for human actors.
Eurographics
2003
Conference-Paper
http://edoc.mpg.de/201856
urn:ISBN:3-905673-54-1
Vision, Video, and Graphics 2003, Eurographics, 9-16 (2003)
en
oai:edoc.mpg.de:2018812010-12-2087:937
Hardware-accelerated Autostereogram Rendering for Interactive 3D Visualization
Petz, Christoph
Goldluecke, Bastian
Magnor, Marcus
Woods, Andrew J.
Merritt, John O.
Benton, Stephen A.
Bolas, Mark T.
Single Image Random Dot Stereograms (SIRDS) are an attractive way of depicting
three-dimensional objects using conventional display technology. Once trained in
decoupling the eyes' convergence and focusing, autostereograms of this kind are
able to convey the three-dimensional impression of a scene. We present in this
work an algorithm that generates SIRDS at interactive frame rates on a
conventional PC. The presented system allows rotating a 3D geometry model and
observing the object from arbitrary positions in real-time. Subjective tests
show that the perception of a moving or rotating 3D scene presents no problem:
The gaze remains focused onto the object. In contrast to conventional SIRDS
algorithms, we render multiple pixels in a single step using a texture-based
approach, exploiting the parallel-processing architecture of modern graphics
hardware. A vertex program determines the parallax for each vertex of the
geometry model, and the graphics hardware's texture unit is used to render the
dot pattern. No data has to be transferred between main memory and the graphics
card for generating the autostereograms, leaving CPU capacity available for
other tasks. Frame rates of 25 fps are attained at a resolution of 1024x512
pixels on a standard PC using a consumer-grade nVidia GeForce4 graphics card,
demonstrating the real-time capability of the system.
SPIE
2003
Conference-Paper
http://edoc.mpg.de/201881
urn:ISBN:0-8194-4806-0
Stereoscopic Displays and Virtual Reality Systems X, SPIE, 359-366 (2003)
en
oai:edoc.mpg.de:2019082010-12-0387:937
Capturing the shape of a dynamic world - fast !
Magnor, Marcus
Seidel, Hans-Peter
Kim, Myung-Soo
IEEE
2003
Conference-Paper
http://edoc.mpg.de/201908
urn:ISBN:0-7695-1909-1
Shape Modeling International 2003 (SMI 2003), IEEE, 3-9 (2003)
en
oai:edoc.mpg.de:2019142010-12-0387:937
Enhancing Silhouette-based Human Motion Capture with 3D Motion Fields
Theobalt, Christian
Carranza, Joel
Magnor, Marcus
Seidel, Hans-Peter
Rokne, Jon
Klein, Reinhard
Wang, Wenping
High-quality non-intrusive human motion capture is necessary for acquistion
of model-based free-viewpoint video of human actors.
Silhouette-based approaches have demonstrated that they are able to
accurately recover a large range of human motion from multi-view video.
However, they fail to make use of all available information, specifically that
of texture information. This paper presents an algorithm
that uses motion fields constructed from optical flow in multi-view video
sequences.
The use of motion fields augments the silhoutte-based method by incorporating
texture-information into the tracking process.
The algorithm is a key-component in a larger free-viewpoint video system of
human actors.
Our results demonstrate that our method accurately estimates pose parameters
and allows for realistic texture generation in 3D video sequences.
IEEE
2003
Conference-Paper
http://edoc.mpg.de/201914
urn:ISBN:0-7695-2028-6
11th Pacific Conference on Computer Graphics and Applications (PG-03), IEEE, 185-193 (2003)
en
oai:edoc.mpg.de:2019182010-12-0387:937
Hardware-Accelerated Visual Hull Reconstruction and Rendering
Li, Ming
Magnor, Marcus
Seidel, Hans-Peter
Möller, Torsten
Ware, Colin
We present a novel algorithm for simultaneous visual hull reconstruction and
rendering by exploiting off-the-shelf graphics hardware. The reconstruction is
accomplished by projective texture mapping in conjunction with alpha test.
Parallel to the reconstruction, rendering is also carried out in the graphics
pipeline. We texture the visual hull view-dependently with the aid of fragment
shaders, such as nVIDIA's register combiners. Both reconstruction and rendering
are done in a single rendering pass. We achieve frame rates of more than 80 fps
on a standard PC equipped with a commodity graphics card. The performance is
significantly faster than previously reported performances of similar systems.
A K Peters
2003
Conference-Paper
http://edoc.mpg.de/201918
urn:ISBN:1-56881-207-8
Graphics Interface 2003 (GI-03), A K Peters, 65-71 (2003)
en
oai:edoc.mpg.de:2019222010-12-0387:937
A Parallel Framework for Silhouette-based Human Motion Capture
Theobalt, Christian
Carranza, Joel
Magnor, Marcus
Seidel, Hans-Peter
Ertl, Thomas
Girod, Bernd
Greiner, Günther
Niemann, Heinrich
Seidel, Hans-Peter
Steinbach, Eckehard
Westermann, Rüdiger
Akademische Verlagsgesellschaft Aka
2003
Conference-Paper
http://edoc.mpg.de/201922
urn:ISBN:3-89838-048-3
Vision, Modeling and Visualization 2003 (VMV-03) : proceedings, Akademische Verlagsgesellschaft Aka, 207-214 (2003)
en
oai:edoc.mpg.de:2019262010-12-0387:937
Sensitivity of Image Formation to Object Surface Orientation
Magnor, Marcus
IEEE
2003
Conference-Paper
http://edoc.mpg.de/201926
urn:ISBN:0-7803-7750-8
IEEE International Conference on Image Processing (ICIP-03), IEEE, 717-720 (2003)
en
oai:edoc.mpg.de:2019292010-12-0387:937
Free-Viewpoint Video of Human Actors
Carranza, Joel
Theobalt, Christian
Magnor, Marcus
Seidel, Hans-Peter
Hodgins, Jessica K.
In free-viewpoint video, the viewer can interactively choose his
viewpoint in \mbox{3-D} space to observe the action of a dynamic
real-world scene from arbitrary perspectives.
The human body and its motion plays a central role in most visual media
and its structure can be exploited for robust motion estimation and efficient
visualization. This paper describes a system that uses multi-view
synchronized video footage of an actor's performance to
estimate motion parameters and to interactively re-render the
actor's appearance from any viewpoint.
The actor's silhouettes are extracted from
synchronized video frames via background
segmentation and then used to determine a sequence of poses
for a \mbox{3D} human body model.
By employing multi-view texturing during rendering, time-dependent changes
in the body surface are reproduced in high detail.
The motion capture subsystem runs offline, is non-intrusive, yields robust
motion parameter estimates, and can cope with a
broad range of motion.
The rendering subsystem runs at real-time frame rates using ubiquous
graphics hardware, yielding a highly naturalistic impression of the
actor.
The actor can be placed in virtual environments to create composite dynamic
scenes. Free-viewpoint video allows the creation of camera fly-throughs or
viewing the action interactively from arbitrary perspectives.
ACM
2003
Conference-Paper
http://edoc.mpg.de/201929
urn:ISSN:0730-0301
Proceedings of ACM SIGGRAPH 2003 (SIGGRAPH-03), ACM, 569-577 (2003)
en
oai:edoc.mpg.de:2019402010-12-0387:937
Multi-View Coding for Image-based Rendering using 3-D Scene Geometry
Magnor, Marcus
Ramanathan, P.
Girod, B.
2003
Article
http://edoc.mpg.de/201940
urn:ISSN:1051-8215
IEEE Transactions on Circuits and Systems for Video Technology, v.13, 1092-1106 (2003)
en
oai:edoc.mpg.de:2019512010-12-0387:937
A Graphics Hardware Implementation of the Generalized Hough Transform for fast Object Recognition, Scale, and 3D Pose Detection
Ihrke, Ivo
Magnor, Marcus
IEEE
2003
Conference-Paper
http://edoc.mpg.de/201951
urn:ISBN:0-7695-1948-2
12th International Conference on Image Analysis and Processing
(ICIAP-03), IEEE, 188-193 (2003)
en
oai:edoc.mpg.de:2019602010-12-0387:937
Real-time Microfacet Billboarding for Free-viewpoint Video Rendering
Goldluecke, Bastian
Magnor, Marcus
We present a hardware-accelerated method for video-based rendering relying on
an approximate model of scene geometry. Our goal is to render high-quality
views of the scene from arbitrary viewpoints in real-time, using as input
synchronized video-streams from only a small number of calibrated cameras
distributed around the scene. Despite the fact that only a very coarse geometry
reconstruction is possible, our rendering approach based on textured billboards
preserves the details present in the source images. By exploiting
multi-texturing and blending facilities
of modern graphics cards, we achieve real-time frame-rates on current
off-the-shelf hardware. One of the possible applications of our algorithm is to
use it in an inexpensive system to display 3D-videos, which the user can watch
from an interactively chosen viewpoint, or ultimately even live 3D-television.
IEEE
2003
Conference-Paper
http://edoc.mpg.de/201960
urn:ISBN:0-7803-7750-8
IEEE International Conference on Image Processing (ICIP-03), IEEE, 713-716 (2003)
en
oai:edoc.mpg.de:2020372010-12-0387:937
Joint 3D-reconstruction and Background Separation in Multiple Views using Graph Cuts
Goldluecke, Bastian
Magnor, Marcus
This paper deals with simultaneous depth map estimation and background
separation in a multi-view setting with several fixed calibrated cameras,
two problems which have previously been addressed separately. We
demonstrate that their strong interdependency can be exploited elegantly
by minimizing a discrete energy functional which evaluates both properties
at the same time. Our algorithm is derived from the powerful
``Multi-Camera Scene Reconstruction via Graph Cuts'' algorithm
recently presented by Kolmogorov and Zabih.
Experiments with both real-world as well
as synthetic scenes demonstrate that the presented combined approach
yields even more correct depth estimates. In particular, the additional
information gained by taking background into account increases considerably
the algorithm's robustness against noise.
IEEE
2003
Conference-Paper
http://edoc.mpg.de/202037
urn:ISBN:0-7695-1900-8
IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR-03), IEEE, 683-694 (2003)
en
oai:edoc.mpg.de:2020422010-12-0387:937
A Solid-State, Simultaneous Wide Angle-Detailed View Video Surveillance Camera
Oi, R.
Magnor, Marcus
Aizawa, K.
Ertl, Thomas
Girod, Bernd
Greiner, Günther
Niemann, Heinrich
Seidel, Hans-Peter
Steinbach, Eckehard
Westermann, Rüdiger
Akademische Verlagsgesellschaft Aka
2003
Conference-Paper
http://edoc.mpg.de/202042
urn:ISBN:3-89839-048-3
Vision, Modeling and Visualization 2003 (VMV-03) : proceedings, Akademische Verlagsgesellschaft Aka, 329-336 (2003)
en
oai:edoc.mpg.de:2022132010-12-0387:937
Numerical Analysis of Time-gated Confocal Microscopy through Anisotropically Scattering Media
Magnor, Marcus
Rudolph, Wolfgang
An efficient and fast simulation technique is
used to calculate the confocal imaging contrast
through anisotropically scattering media when
time-gating techniques are applied. Optimal time-gate
width is found to depend on object reflection
characteristics, and forward-scattering media enhance
imaging contrast only for non-absorbing objects.
OSA
2002
Conference-Paper
http://edoc.mpg.de/202213
urn:ISBN:1-55752-702-4
Proceedings of the OSA Biomedical Topical Meetings, OSA, 56-58 (2002)
en
oai:edoc.mpg.de:2022142010-12-0387:937
Geometry-based Automatic Object Localization and 3-D Pose Detection
Magnor, Marcus
Given the image of a real-world scene and a
polygonal \mbox{3-D} model of a depicted object, its
apparent size, image coordinates, and \mbox{3-D}
orientation are autonomously detected. Based on
matching silhouette outline to edges in the image,
an extensive search in parameter space converges to
the best-matching set of parameter values. Apparent
object size may a-priori be unknown, and no initial
search parameter values need to be provided. Due to
its high degree of parallelism, the algorithm is
well suited for implementation on graphics hardware
to achieve fast object recognition and \mbox{3-D}
pose estimation.
IEEE
2002
Conference-Paper
http://edoc.mpg.de/202214
urn:ISBN:0-7695-1537-1
Proceedings of the 5th IEEE Southwest Symposium on Image Analysis and Interpretation, IEEE, 144-147 (2002)
en
oai:edoc.mpg.de:2022182010-12-0387:937
Multi-Layer Fitting for Online Human Motion Capture
Theobalt, Christian
Magnor, Marcus
Schüler, Pascal
Seidel, Hans-Peter
Greiner, Günther
Niemann, Heinrich
Ertl, Thomas
Girod, Bernd
Seidel, Hans-Peter
aka
2002
Conference-Paper
http://edoc.mpg.de/202218
urn:ISBN:3-89838-034-3
Proceedings Vision, Modeling and Visualization VMV 2002, aka, 471-478 (2002)
en
oai:edoc.mpg.de:2022192010-12-0387:937
Combining 2D Feature Tracking and Volume Reconstruction for Online Video-based Human Motion Capture
Theobalt, Christian
Magnor, Marcus
Schüler, Pascal
Seidel, Hans-Peter
Coquillart, Sabine
Shum, Heung-Yeung
Hu, Shi-Min
IEEE
2002
Conference-Paper
http://edoc.mpg.de/202219
urn:ISBN:0-7695-1784-6
Proceedings IEEE Pacific Graphics 2002, IEEE, 96-103 (2002)
en
oai:edoc.mpg.de:2022202010-12-0387:937
An X-Ray, Optical, and Radio Search for Supernova Remnants in the Nearby Sculptor Group Sd Galaxy NGC 7793
Pannuti, T.
Duric, N.
Lacey, C.
Ferguson, A.
Magnor, Marcus
Mendelowitz, C.
2002
Article
http://edoc.mpg.de/202220
urn:ISSN:0004-637X
Astrophysical Journal, v.565, 966-981 (2002)
en
oai:edoc.mpg.de:2022332010-12-0387:937
Interactive Rendering of Translucent Objects
Lensch, Hendrik
Gösele, Michael
Bekaert, Philippe
Kautz, Jan
Magnor, Marcus
Lang, Jochen
Seidel, Hans-Peter
Coquillart, Sabine
Shum, Heung-Yeung
Hu, Shi-Min
IEEE
2002
Conference-Paper
http://edoc.mpg.de/202233
urn:ISBN:0-7695-1784-6
Proceedings IEEE Pacific Graphics 2002, IEEE, 214-224 (2002)
en
oai:edoc.mpg.de:2022342010-12-0387:937
Hardware-accelerated Dynamic Light Field Rendering
Goldluecke, Bastian
Magnor, Marcus
Wilburn, Bennett
Greiner, Günther
Niemann, Heinrich
Ertl, Thomas
Girod, Bernd
Seidel, Hans-Peter
We present a system capable of interactively displaying a dynamic scene from
novel viewpoints by warping and blending images recorded from multiple
synchronized video cameras.
It is tuned for streamed data and achieves 20~frames per second on modern
consumer-class hardware when rendering a 3D~movie from an arbitrary eye point
within the convex hull of the recording camera's positions.
The quality of the prediction largely depends on the accuracy of the disparity
maps which are reconstructed off-line and provided together with the images. We
generalize known algorithms for estimating disparities between two images
to the case of multiple image streams, aiming at a minimization of warping
artifacts and utilization of temporal coherence.
aka
2002
Conference-Paper
http://edoc.mpg.de/202234
urn:ISBN:3-89838-034-3
Proceedings Vision, Modeling and Visualization VMV 2002, aka, 455-462 (2002)
en
oai:edoc.mpg.de:2022352010-12-0387:937
Combining Stereo and Visual Hull Information for On-line Reonstruction and Rendering of Dynamic Scenes
Li, Ming
Schirmacher, Hartmut
Magnor, Marcus
Seidel, Hans-Peter
Ostermann, Joern
Zhuang, Xinhua
IEEE
2002
Conference-Paper
http://edoc.mpg.de/202235
urn:ISBN:0-7803-7713-3
Proceedings IEEE Multimedia Signal Processing Workshop MMSP-2002, IEEE, 9-12 (2002)
en
oai:edoc.mpg.de:2317972010-12-0387:937
Model-Based Free-Viewpoint Video Acquisition, Rendering and Encoding
Theobalt, Christian
Ziegler, Gernot
Magnor, Marcus
Seidel, Hans-Peter
UC Davis
2004
Conference-Paper
http://edoc.mpg.de/231797
Picture Coding Symposium 2004 (PCS-04), UC Davis, SpecialSession5,1-6 (2004)
en
oai:edoc.mpg.de:2318002010-12-0387:937
A Mobile System for Multi-Video Recording
Ahrenberg, Lukas
Ihrke, Ivo
Magnor, Marcus
\begin{abstract}
We present a portable system to record synchronised, multi-video data
for vision applications such as 3D
reconstruction and video-based rendering of dynamic scenes.
The aim of the project is
to gain access to a greater number of scenes than what a static, wired
indoor studio allows for. The portable acquisition system is
constructed from a number of independent modules, each consisting of
a FireWire camera and a laptop. Our software utilises wireless
networking making the system behave
like a tightly coupled unit without requiring the modules to be
physically connected to each other. The scheme also includes an
external calibration method suitable for general scenes.
The system is scalable and
allows for easy transportation and ad-hoc setup and configuration. We present
recent result
s acquired in the field and their use for free-viewpoint video.
\end{abstract}
Institution of Electrical Engineers
2004
Conference-Paper
http://edoc.mpg.de/231800
urn:ISBN:0863413919
1st European Conference on Visual Media Production (CVMP), Institution of Electrical Engineers, 127-132 (2004)
en
oai:edoc.mpg.de:2318012010-12-0387:937
Spacetime-coherent Geometry Reconstruction from Multiple Video Streams
Magnor, Marcus
Goldluecke, Bastian
Aloimonos, Y.
IEEE
2004
Conference-Paper
http://edoc.mpg.de/231801
urn:ISBN:0-7695-2223-8
2nd International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2004, IEEE, 365-372 (2004)
en
oai:edoc.mpg.de:2318022010-12-0387:937
Cloth Motion from Optical Flow
Scholz, Volker
Magnor, Marcus
Girod, B.
Magnor, M.
Seidel, H.-P.
This paper presents an algorithm for capturing the motion of deformable
surfaces, in particular textured cloth. In a calibrated multi-camera setup, the
optical flow between consecutive video frames is determined and 3D scene flow
is computed. We use a deformable surface model with constraints for vertex
distances and curvature to increase the robustness of the optical flow
measurements. Tracking errors in long video sequences are corrected by a
silhouette matching procedure. We present results for synthetic cloth
simulations and discuss how they can be extended to real-world footage.
Akademische Verlagsgesellschaft Aka
2004
Conference-Paper
http://edoc.mpg.de/231802
urn:ISBN:3-89838-058-0
Vision, modeling, and visualization 2004 (VMV-04), Akademische Verlagsgesellschaft Aka, 117-124 (2004)
en
oai:edoc.mpg.de:2318062010-12-0387:937
Constrained Inverse Volume Rendering for Planetary Nebulae
Magnor, Marcus
Kindlmann, Gordon
Hansen, Charles
Duric, Neb
Rushmeier, Holly
Turk, Greg
van Wijk, Jarke J.
IEEE
2004
Conference-Paper
http://edoc.mpg.de/231806
urn:ISBN:0-7803-8788-0
IEEE Visualization 2004 : VIS 2004, IEEE, 83-90 (2004)
en
oai:edoc.mpg.de:2318082010-12-0387:937
3D-TV - Future of Visual Entertainment
Magnor, Marcus
Abate, A.F.
Nappi, M.
Sebillo, M.
World Scientific
2004
Conference-Paper
http://edoc.mpg.de/231808
urn:ISBN:981-256-137-4
Multimedia databases and image communication (MDIC-04): Proceedings of the Workshop on MDIC 2004, World Scientific, 105-112 (2004)
en
oai:edoc.mpg.de:2318102010-12-0387:937
External camera calibration for synchronized multi-video systems
Ihrke, Ivo
Ahrenberg, Lukas
Magnor, Marcus
UNION Agency
2004
Conference-Paper
http://edoc.mpg.de/231810
urn:ISSN:1213-6972
WSCG '2004 : the 12th International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision 2004 ; short communication papers proceedings, UNION Agency, 537-544 (2004)
en
oai:edoc.mpg.de:2318162010-12-0387:937
3D-TV - Computergraphik zwischen virtueller und realer Welt
Magnor, Marcus
2004
Article
http://edoc.mpg.de/231816
urn:ISSN:0170-6012
Informatik Spektrum, v.27, 497-503 (2004)
en
oai:edoc.mpg.de:2318192010-12-0387:937
Image-Based Tomographic Reconstruction of Flames
Ihrke, Ivo
Magnor, Marcus
Boulic, R.
Pai, D.K.
Eurographics Association
2004
Conference-Paper
http://edoc.mpg.de/231819
urn:ISBN:3-905673-14-2
Computer Animation 2004 : ACM SIGGRAPH / Eurographics Symposium on Computer Animation, Eurographics Association, 367-375 (2004)
en
oai:edoc.mpg.de:2318202010-12-0387:937
Weighted Minimal Hypersurfaces and Their Applications in Computer Vision
Goldluecke, Bastian
Magnor, Marcus
Pajdla, Tomás
Matas, Jirí
Many interesting problems in computer vision can be formulated as a
minimization problem for an {\em energy functional}.
If this functional is given as an integral of a scalar-valued weight function
over an unknown hypersurface, then the minimal surface we are looking for can
be determined as a solution of the functional's Euler-Lagrange equation.
This paper deals with a general class of weight functions
that may depend on the surface point and normal.
By making use of a mathematical tool called {\em the method of the moving
frame},
we are able to derive the Euler-Lagrange equation in arbitrary-dimensional
space and without the need for any surface parameterization.
Our work generalizes existing proofs, and we demonstrate that it
yields the correct evolution equations for a variety of previous
computer vision techniques which can be expressed in terms of our
theoretical framework.
In practical applications, the surface evolution which converges to a
solution of the Euler-Lagrange equation can be implemented using level
set techniques.
The well-known transition to a level set evolution equation,
which we briefly review in this paper, works in the general case as well.
That way, problems involving minimal hypersurfaces in dimensions higher than
three,
which were previously impossible to solve in practice, can now be introduced
and handled by generalized versions of existing algorithms.
As one example, we sketch a novel idea how to reconstruct
temporally coherent geometry from multiple video streams.
Springer
2004
Conference-Paper
http://edoc.mpg.de/231820
urn:ISBN:3-540-21983-8
Computer vision, ECCV 2004 : 8th European Conference on Computer Vision - part II, Springer, 366-378 (2004)
en
oai:edoc.mpg.de:2318212010-12-0387:937
Space-Time Isosurface Evolution for Temporally Coherent 3D Reconstruction
Goldluecke, Bastian
Magnor, Marcus
We model the dynamic geometry of a time-varying scene as a 3D isosurface in
space-time.
The intersection of the isosurface with planes of constant time yields the
geometry at a
single time instant.
An optimal fit of our model to multiple video sequences is
defined as the minimum of an energy functional.
This functional is given by an integral over the entire hypersurface,
which is designed to optimize photo-consistency.
A PDE-based evolution derived from the Euler-Lagrange equation
maximizes consistency with all of the given video data simultaneously.
The result is a 3D model of the scene which varies smoothly over time.
The geometry reconstructed by this scheme
is significantly better than results obtained by space-carving approaches
that do not enforce temporal coherence.
IEEE
2004
Conference-Paper
http://edoc.mpg.de/231821
urn:ISBN:0-7695-2158-4
Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2004, IEEE, 350-355 (2004)
en
oai:edoc.mpg.de:2416142010-12-0387:937
M3: Marker-free Model Reconstruction and Motion Tracking from 3D Voxel Data
de Aguiar, Edilson
Theobalt, Christian
Magnor, Marcus
Theisel, Holger
Seidel, Hans-Peter
IEEE
2004
Conference-Paper
http://edoc.mpg.de/241614
urn:ISBN:0-7395-2234-3
Cohen-Or, Daniel; Ko, Hyeong-Seok; Terzopoulos, Demetri; Warren, Joe: Proceedings of the 12th Pacific Conference on Computer Graphics and Applications, PG 2004, IEEE, 101-110 (2004)
en
oai:edoc.mpg.de:2416152010-12-0387:937
Hardware-Accelerated Rendering of Photo Hulls
Li, Ming
Magnor, Marcus
Seidel, Hans-Peter
Cani, Marie-Paule
Slater, Mel
Blackwell
2004
Conference-Paper
http://edoc.mpg.de/241615
urn:ISSN:0167-7055
The European Association for Computer Graphics 25th Annual Conference EUROGRAPHICS 2004, Blackwell, 635-642 (2004)
en
oai:edoc.mpg.de:2416172010-12-0387:937
A Hybrid Hardware-Accelerated Algorithm for High Quality Rendering of Visual Hulls
Li, Ming
Magnor, Marcus
Seidel, Hans-Peter
Heidrich, Wolfgang
Balakrishnan, Ravin
Canadian Information Processing Society
2004
Conference-Paper
http://edoc.mpg.de/241617
urn:ISBN:1-56881-227-2
Graphics Interface 2004 (GI-04) : proceedings, Canadian Information Processing Society, 41-48 (2004)
en
oai:edoc.mpg.de:2416182010-12-0387:937
Model-based Analysis of Multi-Video Data
Magnor, Marcus
Theobalt, Christian
IEEE
2004
Conference-Paper
http://edoc.mpg.de/241618
urn:ISBN:0-7803-8387-7
6th IEEE Southwest Symposium on Image Analysis and Interpretation, 2004 (SSIAI'2004), IEEE, 41-45 (2004)
en
oai:edoc.mpg.de:2416202010-12-0387:937
Pitching a Baseball - Tracking High-Speed Motion with Multi-Exposure Images
Theobalt, Christian
Albrecht, Irene
Haber, Joerg
Magnor, Marcus
Seidel, Hans-Peter
Marks, Joe
2004
Conference-Paper
http://edoc.mpg.de/241620
ACM Transactions on Graphics, v.23, 3, 540-547 (2004)
en
oai:edoc.mpg.de:2416212010-12-0387:937
Combining 3D Flow Fields with Silhouette-based Human Motion Capture for Immersive Video
Theobalt, Christian
Carranza, Joel
Magnor, Marcus
Seidel, Hans-Peter
2004
Article
http://edoc.mpg.de/241621
urn:ISSN:1524-0703
Graphical Models, v.66, 333-351 (2004)
en
oai:edoc.mpg.de:2416222010-12-0387:937
3D Video - Being Part of the Movie
Theobalt, Christian
Carranza, Joel
Magnor, Marcus
Seidel, Hans-Peter
2004
Article
http://edoc.mpg.de/241622
urn:ISSN:0097-8930
ACM Computer Graphics, v.38, 18-20 (2004)
en
oai:edoc.mpg.de:2416232010-12-0387:937
Marker-free Kinematic Skeleton Estimation from Sequences of Volume Data
Theobalt, Christian
de Aguiar, Edilson
Magnor, Marcus
Theisel, Holger
Seidel, Hans-Peter
Lau, Rynson
Baciu, George
ACM
2004
Conference-Paper
http://edoc.mpg.de/241623
urn:ISBN:1-58113-907-1
Lau, Rynson; Baciu, George: Proceedings of the ACM Symposium on Virtual Reality Software and Technology (VRST'04), ACM, 57-64 (2004)
en
oai:edoc.mpg.de:2416242010-12-0387:937
Combining 2D Feature Tracking and Volume Reconstruction for Online Video-based Human Motion Capture
Theobalt, Christian
Magnor, Marcus
Schüler, Pascal
Seidel, Hans-Peter
2004
Article
http://edoc.mpg.de/241624
urn:ISBN:02194678
International Journal of Image and Graphics, v.4, 563-583 (2004)
en
oai:edoc.mpg.de:2416252010-12-0387:937
Multi-Video Compression in Texture Space
Ziegler, Gernot
Lensch, Hendrik P. A.
Ahmed, Naveed
Magnor, Marcus
Seidel, Hans-Peter
We present a model-based approach to encode multiple synchronized
video streams depicting a dynamic scene from different viewpoints.
With approximate 3D scene geometry available, we compensate for
motion as well as disparity by transforming all video images
to object textures prior to compression.
A two-level hierarchical coding strategy is employed to efficiently
exploit inter-texture coherence as well as to ensure quick random
access during decoding.
Experimental validation shows that attainable compression ratios
range up to 50:1 without subsampling.
The proposed coding scheme is intended for use in conjunction with
Free-Viewpoint Video and 3D-TV applications.
IEEE
2004
Conference-Paper
http://edoc.mpg.de/241625
urn:ISBN:0-7803-8555-1
11th IEEE International Conference on Image Processing (ICIP 2004), IEEE, 2467-2470 (2004)
en
oai:edoc.mpg.de:2416262010-12-0387:937
Multi-Video Compression in Texture Space using 4D SPIHT
Ziegler, Gernot
Lensch, Hendrik
Magnor, Marcus
Seidel, Hans-Peter
IEEE
2004
Conference-Paper
http://edoc.mpg.de/241626
urn:ISBN:0-7803-8579-9
2004 IEEE 6th Workshop on Multimedia Signal Processing (MMSP'04), IEEE, 39-42 (2004)
en
oai:edoc.mpg.de:5207012010-12-0387:937
Learning Flames
Stich, Timo
Magnor, Marcus
In this work we propose a novel approach for realistic fire animation and
manipulation. We apply a statistical learning method to an image sequence of a
real-world flame to jointly capture flame motion and appearance
characteristics. A low-dimensional generic flame model is then robustly matched
to the video images. The model parameter values are used as input to drive an
Expectation-Maximization algorithm to learn an {\em auto regressive process}
with respect to flame dynamics. The generic flame model and the trained motion
model enable us to synthesize new, unique flame sequences of arbitrary length
in real-time.
Akademische Verlagsgesellschaft Aka
2005
Conference-Paper
http://edoc.mpg.de/520701
urn:ISBN:3-89838-068-8
Greiner, Günther; Hornegger, Joachim; Niemann, Heinrich; Stamminger, Marc: Vision, Modeling, and Visualization 2005 (VMV'05), Akademische Verlagsgesellschaft Aka, 60-65 (2005)
en
oai:edoc.mpg.de:5207022010-12-0387:937
Reflection Nebula Visualization
Magnor, Marcus
Hildebrand, Kristian
Lintu, Andrei
Hanson, Andrew J.
IEEE
2005
Conference-Paper
http://edoc.mpg.de/520702
urn:ISBN:0-7803-9462-3
Silva, C.T.; Gröller, E.; Rushmeier, H.: IEEE Visualization 2005 : VIS 2005, IEEE, 255-262 (2005)
en
oai:edoc.mpg.de:5207032010-12-0387:937
Reconstructing the Geometry of Flowing Water
Ihrke, Ivo
Goldluecke, Bastian
Magnor, Marcus
IEEE
2005
Conference-Paper
http://edoc.mpg.de/520703
urn:ISBN:0-7695-2334-X
VISION '05 : proceedings of the 2005 International Conference on Computer Vision (ICCV'05), IEEE, 1055-1060 (2005)
en
oai:edoc.mpg.de:5207042010-12-0387:937
Augmented Astronomical Telescope
Lintu, Andrei
Magnor, Marcus
Shaker
2005
Conference-Paper
http://edoc.mpg.de/520704
urn:ISBN:3-8322-4431-X
Kuhlen, Torsten; Kobbelt, Leif; Müller, S.: Virtuelle und erweiterte Realität : 2. Workshop der GI-Fachgruppe VR/AR, Shaker, 203-213 (2005)
en
oai:edoc.mpg.de:5207052010-12-0387:937
Adaptive Grid Optical Tomography
Ihrke, Ivo
Magnor, Marcus
Eurographics
2005
Conference-Paper
http://edoc.mpg.de/520705
urn:ISBN:3-905673-57-6
Fellner, Dieter: Vision, Video, and Graphics 2005, Eurographics, 141-147 (2005)
en
oai:edoc.mpg.de:5207062010-12-0387:937
3D Image Analysis and Synthesis at {MPI} Informatik
Theobalt, Christian
Magnor, Marcus
Seidel, Hans-Peter
Eurographics
2005
Conference-Paper
http://edoc.mpg.de/520706
urn:ISBN:3-905673-57-6
Fellner, Dieter: Vision, Video, and Graphics 2005, Eurographics, 85-92 (2005)
en
oai:edoc.mpg.de:5207072011-04-2087:937
Reconstruction and Visualization of Planetary Nebulae
Magnor, Marcus
Kindlmann, Gordon
Hansen, C.
Duric, N.
2005
Article
http://edoc.mpg.de/520707
urn:ISSN:1077-2626
IEEE Transactions on Visualization and Computer Graphics, v.11, 485-496 (2005)
en
oai:edoc.mpg.de:5207082010-12-0387:937
Light Field Rendering using Matrix Optics
Ahrenberg, Lukas
Magnor, Marcus
This paper presents a light field rendering framework based on matrix optics.
Matrix optics, in contrast to intersection-based methods such as ray-tracing,
has
the advantage that a generic series of optic operators can be combined into a
single matrix.
This enables us to realize a ``virtual optical bench'' where different setups
can be
easily tested.
We introduce the theoretical foundation of matrix optics and define a set of
operators
suitable for light fields. We then discuss a wavelet compression scheme
for our light field representation. Finally we introduce a real-time rendering
approach based on
matrix optics suitable for both uncompressed and compressed light fields.
Permission
to make digital or hard copies of all or part of this work for personal or
classroom
use is granted without fee provided that copies are not made or distributed for
profit or commercial advantage and that copies bear this notice and the
full citation on the first page. To copy otherwise, or republish, to post on
servers or to redistribute to lists, requires prior specific permission and/or
a fee.
2006
Article
http://edoc.mpg.de/520708
urn:ISSN:1213-6972
Journal of WSCG, v.14, 177-184 (2006)
en
oai:edoc.mpg.de:5207102010-12-0387:937
Garment Motion Capture Using Color-Coded Patterns
Scholz, Volker
Stich, Timo
Magnor, Marcus
Keckeisen, Michael
Wacker, Markus
ACM SIGGRAPH
2005
Conference-Paper
http://edoc.mpg.de/520710
Buhler, Juan: ACM SIGGRAPH Sketches and Applications, ACM SIGGRAPH (2005)
en
oai:edoc.mpg.de:5207112010-12-0387:937
An Augmented Reality System for Astrnomical Observations
Lintu, Andrei
Magnor, Marcus
Anyone who has gazed through the eyepiece of an astronomical telescope knows
that, with the exception of the Moon and the planets, extra-solar astronomical
objects are disappointing to observe visually. This is mainly due to their low
surface brightness, but also depends on the visibility, sky brightness and
telescope aperture. We propose a system which projects images of astronomical
objects (with focus on nebulae and galaxies),
animations and additional information directly into the eyepiece view of an
astronomical telescope. As the telescope orientation is queried continuously,
the projected image is adapted in real-time to the currently visible field of
view. For projection, a custom-built video projection module with high contrast
and low maximum luminance value was developed. With this technology visitors to
public observatories have the option to experience the richness of faint
astronomical objects while directly looking at them through a telescope.
IEEE
2006
Conference-Paper
http://edoc.mpg.de/520711
urn:ISBN:1-4244-0223-9
Froelich, Bernd; Bowman, Doug; Iwata, Hiroo: IEEE Virtual Reality 2006, IEEE, 119-126 (2006)
en
oai:edoc.mpg.de:5207132010-12-0387:937
Automatic Generation of Personalized Human Avatars from Multi-View Video
Ahmed, Naveed
de Aguiar, Edilson
Theobalt, Christian
Magnor, Marcus
Seidel, Hans-Peter
ACM
2005
Conference-Paper
http://edoc.mpg.de/520713
urn:ISBN:1-59593-098-1
VRST '05: Proceedings of the ACM symposium on Virtual reality software and technology, ACM, 257-260 (2005)
en
oai:edoc.mpg.de:5207162010-12-0387:937
Texture Replacement of Garments in Monocular Video Sequences
Scholz, Volker
Magnor, Marcus
In this paper, we present a video processing algorithm for texture replacement
of moving garments in monocular video recordings. We use a color-coded pattern
which encodes texture coordinates within a local neighborhood in order to
determine the geometric deformation of the texture. A time-coherent texture
interpolation is obtained by the use of 3D radial basis functions. Shading maps
are determined with a surface reconstruction technique and applied to new
textures which replace the color pattern in the video sequence. Our method
enables exchanging fabric pattern designs of garments worn by actors as a video
post-processing step.
Eurographics
2006
Conference-Paper
http://edoc.mpg.de/520716
urn:ISBN:1-56881-351-1
Fellner, Dieter W.; Spencer, Stephen N.; Chrysanthou, Yiorgos; Cohen-Or, Daniel; Akenine-Möller, Tomas; Heidrich, Wolfgang: Rendering Techniques 2006 : Eurographics Symposium on Rendering, Eurographics, 305-312 (2006)
en
oai:edoc.mpg.de:5207172010-12-0387:937
Multi-View Video Capture of Garment Motion
Scholz, Volker
Magnor, Marcus
We present an image-based algorithm for surface reconstruction of moving
garments from multiple calibrated video cameras. Using a color-coded cloth
texture, we reliably match circular features between different camera views. As
surface model we use an a priori known triangle mesh. By identifying the mesh
vertices with texture elements we obtain a coherent parametrization of the
surface over time without further processing. Missing data points resulting
from self-shadowing are plausibly interpolated by minimizing a thin-plate
functional. The deforming geometry can be used for different graphics
applications, e.g. for realistic retexturing. We show results for real garments
demonstrating the accuracy of the recovered flexible shape.
Technische Universiteit Eindhoven
2006
Conference-Paper
http://edoc.mpg.de/520717
urn:ISBN:978-90-386-2062-6
de With, Peter H.N.; Varekamp, Chris; Farin, Dirk S.; Morvan, Yannick: Content Generation and Coding for 3D-Television, Technische Universiteit Eindhoven, 1-4 (2006)
en
oai:edoc.mpg.de:5207182010-12-0387:937
Computer generated holography using parallel commodity graphics hardware
Ahrenberg, Lukas
Benzie, Philip
Magnor, Marcus
Watson, John
This paper presents a novel method for using programmable graphics hardware to
generate fringe patterns for SLM-based
holographic displays. The algorithm is designed to take the programming
constraints imposed by the graphics hardware pipeline
model into consideration, and scales linearly with the number of object points.
In contrast to previous methods we do not have to use the Fresnel
approximation. The technique can also be used on
several graphics processors in parallel for further optimization.
We achieve real-time frame rates for objects consisting of a few hundred
points at a resolution of
$960 \times 600$ pixels and over $10$ frames per second for $1000$ points.
2006
Article
http://edoc.mpg.de/520718
urn:ISSN:1094-4087
Optics Express, v.14, 7636-7641 (2006)
en
oai:edoc.mpg.de:5207192010-12-0387:937
Adaptive grid optical tomography
Ihrke, Ivo
Magnor, Marcus
Image-based modeling of semi-transparent, dynamic phenomena is a challenging
task. We present an optical tomography method that uses an adaptive grid for
the reconstruction of a three-dimensional density function from its
projections. The proposed method is applied to reconstruct thin smoke and
flames volumetrically from synchronized multi-video recordings. Our adaptive
reconstruction algorithm computes a time-varying volumetric model, that enables
the photorealistical rendering of the recorded phenomena from arbitrary
viewpoints. In contrast to previous approaches we sample the underlying
unknown, three-dimensional density function adaptively which enables us to
achieve a higher effective resolution of the reconstructed models.
2006
Article
http://edoc.mpg.de/520719
urn:ISSN:1524-0703
Graphical Models, v.68, 484-495 (2006)
en
oai:edoc.mpg.de:5207202010-12-0387:937
Effective Multi-resolution Rendering and Texture Compression for Captured Volumetric Trees
Linz, Christian
Drettakis, George
Magnor, Marcus
Reche-Martinez, Alex
Trees can be realistically rendered in synthetic environments by creating
volumetric representations from photographs. Volumetric trees created with
previous methods are expensive to render due to the high number of primitives,
and have very high texture memory requirements. We present an efficient
multi-resolution rendering method and an effective texture compression
solution, addressing both shortcomings.
Our method uses an octree with appropriate textures at intermediate hierarchy
levels and applies an effective pruning strategy. For texture compression, we
adapt a vector quantization approach to use a perceptually accurate colour
space, and modify the codebook generation of the Generalized Lloyd Algorithm to
further improve texture quality. Combined with several hardware accelerations,
our approach achieves a two orders of magnitude
reduction in texture memory requirements; in addition, it is now possible to
render tens or even hundreds of captured trees at interactive rates.
Eurographics
2006
Conference-Paper
http://edoc.mpg.de/520720
Galin, Eric; Chiba, Norishige: Proceedings of the Eurographics Workshop on Natural Phenomena, Eurographics, 83-90 (2006)
en
oai:edoc.mpg.de:5207212010-12-0387:937
A Point-based Approach to PDE-based Surface Reconstruction
Linz, Christian
Goldluecke, Bastian
Magnor, Marcus
Variational techniques are a popular approach for reconstructing the surface of
an object. In previous work, the surface is represented either implicitly by
the use of level sets or explicitly as a triangle mesh. In this paper we
describe new formulations and develop fast algorithms for surface
reconstruction based on partial differential equations (PDEs) derived from
variational calculus using an explicit, purely point-based surface
representation. The method is based on a Moving Least-Squares surface
approximation of the sample points. Our new approach automatically copes with
complicated topology and deformations, without the need for explicit treatment.
In contrast to level sets, it requires no postprocessing, easily adapts to
varying spatial resolutions and is invariant under rigid body motion. We
demonstrate the versatility of our method using several synthetic data sets and
show how our technique can be used to reconstruct object surfaces from
real-world multi-view footage.
Springer
2006
Conference-Paper
http://edoc.mpg.de/520721
urn:ISBN:978-3-540-44412-1
Franke, Katrin; Müller, Klaus R.; Nickolay, Bertram; Schäfer, Ralf: Pattern Recognition : 28th DAGM Symposium (DAGM'06), Springer, 729-738 (2006)
en
oai:edoc.mpg.de:5207222010-12-0387:937
Weighted Minimal Hypersurface Reconstruction
Goldluecke, Bastian
Ihrke, Ivo
Linz, Christian
Magnor, Marcus
Many problems in computer vision can be formulated as a minimization problem
for an energy functional. If this functional is given as an integral of a
scalar-valued weight function over an unknown hypersurface, then the
sought-after minimal surface can be determined as a solution of the
functional's Euler-Lagrange equation. This paper deals with a general class of
weight functions that may depend on surface point coordinates as well as
surface orientation. We derive the Euler-Lagrange equation in arbitrary
dimensional space without the need for any surface parameterization,
generalizing existing proofs. Our work opens up the possibility of solving
problems involving minimal hypersurfaces in a dimension higher than three,
which were previously impossible to solve in practice. We also introduce two
applications of our new framework: We show how to reconstruct temporally
coherent geometry from multiple video streams, and we use the same framework
for the volumetric reconstruction of refractive and transparent natural
phenomena, here bodies of flowing water.
2007
Article
http://edoc.mpg.de/520722
info:doi/10.1109/TPAMI.2007.1146
IEEE Transactions on Pattern Analysis and Machine Intelligence, v.29, 1194-1208 (2007)
en
oai:edoc.mpg.de:5207252010-12-0387:937
A Bidirectional Light Field - Hologram Transform
Ziegler, Remo
Bucheli, Simon
Ahrenberg, Lukas
Magnor, Marcus
Gross, Markus
Blackwell Publishing
2007
Conference-Paper
http://edoc.mpg.de/520725
urn:ISSN:0167+7055
Cohen Or, Danny; Slavik, Pavel: Computer Graphics Forum, Blackwell Publishing, 435-446 (2007)
en
oai:edoc.mpg.de:5207262010-12-0387:937
Realistic Solar Disc Rendering
Lintu, Andrei
Haber, Jörg
Magnor, Marcus
University of West Bohemia
2005
Conference-Paper
http://edoc.mpg.de/520726
urn:ISBN:80-903100-7-9
Skala, Vaclav: WSCG 2005, the 13th International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision 2005 : in co-operation with EUROGRAPHICS W S C G ' 2005, FULL PAPERS, University of West Bohemia, 79-86 (2005)
en
oai:edoc.mpg.de:5207272010-12-0387:937
Volumetric Reconstruction, Compression and Rendering of Natural Phenomena from Multi-Video Data
Ahrenberg, Lukas
Ihrke, Ivo
Magnor, Marcus
\begin{abstract}
Lately, new methods for the acquisition of time-varying, volumetric data for
photo-realistic rendering of semi-transparent, volumetric
phenomena like fire and smoke have been developed. This paper presents a
wavelet-coding and rendering approach for these volumetric sequences that
exploits spatial as well as temporal coherence in the data. A space
partitioning tree
allows for efficient storage and real-time rendering of dynamic, volumetric
data on
common PC hardware.
\end{abstract}
Eurographics
2005
Conference-Paper
http://edoc.mpg.de/520727
urn:ISBN:3-905673-26-6
Gröller, Eduard; Fujishiro, I.; Müller, Klaus; Ertl, T.: Volume graphics 2005 : Eurographics/IEEE VGTC workshop proceedings ; Fourth International Workshop on Volume Graphics, Eurographics, 83-90 (2005)
en
oai:edoc.mpg.de:5207282010-12-0487:937
Garment Motion Capture Using Color-Coded Patterns
Scholz, Volker
Stich, Timo
Keckeisen, Michael
Wacker, Markus
Magnor, Marcus
In this paper we present an image-based algorithm for surface reconstruction of
moving garment from multiple calibrated video cameras. Using a color-coded
cloth texture, we reliably match circular features between different camera
views. As surface model we use an a priori known triangle mesh. By identifying
the mesh vertices with texture elements we obtain a consistent parameterization
of the surface over time without further processing. Missing data points
resulting from self-shadowing are plausibly interpolated by minimizing a
thin-plate functional. The deforming geometry can be used for different
graphics applications, e.g. for realistic retexturing. We show results for real
garments demonstrating the accuracy of the recovered flexible shape.
2005
Article
http://edoc.mpg.de/520728
urn:ISSN:0167-7055
Computer Graphics Forum, v.24, 439-448 (2005)
en
oai:edoc.mpg.de:5207292010-12-0387:937
Space-time continuous geometry meshes from multi-view video sequences
Goldluecke, Bastian
Magnor, Marcus
We reconstruct geometry for a time-varying scene given by
a number of video sequences.
The dynamic geometry is represented by a 3D
hypersurface embedded in space-time.
The intersection of the hypersurface with planes of constant time
then yields the geometry at a single time instant.
In this paper, we model the hypersurface with a collection of triangle
meshes, one for each time frame.
The photo-consistency error is measured by an error functional defined as
an integral over the hypersurface.
It can be minimized using a PDE driven surface evolution, which
simultaneously optimizes space-time continuity as well.
Compared to our previous implementation based on level sets, triangle
meshes yield more accurate results, while requiring less memory and
computation time.
Meshes are also directly compatible with triangle-based rendering
algorithms, so no additional post-processing is required.
IEEE
2005
Conference-Paper
http://edoc.mpg.de/520729
2005 International Conference on Image Processing (ICIP), IEEE, 625-628 (2005)
en
oai:edoc.mpg.de:5207302010-12-0387:937
Video-based Rendering
Magnor, Marcus
A K Peters
2005
Book
http://edoc.mpg.de/520730
urn:ISBN:1-56881-244-2
en
oai:edoc.mpg.de:5207322010-12-0387:937
Physically based Simulation of Twilight Phenomena
Haber, Jörg
Magnor, Marcus
Seidel, Hans-Peter
We present a physically based approach to compute the colors of the sky during
the twilight period before sunrise and after sunset. The simulation is based
on the theory of light scattering by small particles. A realistic atmosphere
model is assumed, consisting of air molecules, aerosols, and water. Air
density, aerosols, and relative humidity vary with altitude. In addition, the
aerosol component varies in composition and particle size distribution. This
allows us to realistically simulate twilight phenomena for a wide range of
different climate conditions. Besides considering multiple Rayleigh and Mie
scattering, we take into account wavelength-dependent refraction of direct
sunlight as well as the shadow of the Earth. Incorporating several
optimizations into the radiative transfer simulation, a photo-realistic
hemispherical twilight sky is computed in less than two hours on a conventional
PC. The resulting radiometric data is useful, for instance, for high-dynamic
range environment mapping, outdoor global illumination calculations, mesopic
vision research and optical aerosol load probing.
2005
Article
http://edoc.mpg.de/520732
urn:ISSN:0730-0301
Transactions on Graphics, v.24, 1353-1373 (2005)
en