Filters








668 Hits in 4.8 sec

Head-mounted photometric stereo for performance capture

Andrew Jones, Graham Fyffe, Xueming Yu, Alex Ma, Jay Busch, Mark Bolas, Paul Debevec
2010 ACM SIGGRAPH 2010 Talks on - SIGGRAPH '10  
We have developed a system that augments a head-mounted camera with LED-based photometric stereo.  ...  Head-mounted cameras are an increasingly important tool for capturing facial performances to drive virtual characters.  ...  Head-mounted photometric stereo captures an entire face, not just a sparse set of motion capture markers.  ... 
doi:10.1145/1837026.1837088 dblp:conf/siggraph/JonesFYMBBD10 fatcat:p42uvy2u2vhyxac5xt35tg2any

FaceVR: Real-Time Facial Reenactment and Eye Gaze Control in Virtual Reality [article]

Justus Thies, Michael Zollhöfer, Marc Stamminger, Christian Theobalt, Matthias Nießner
2018 arXiv   pre-print
The key component of FaceVR is a robust algorithm to perform real-time facial motion capture of an actor who is wearing a head-mounted display (HMD), as well as a new data-driven approach for eye tracking  ...  While they achieve good tracking performance the results look cartoonish and not real.  ...  ACKNOWLEDGMENTS We thank Angela Dai for the video voice over and all actors for the VR reenactment. The facial landmark tracker was kindly provided by TrueVisionSolution.  ... 
arXiv:1610.03151v2 fatcat:pnx2nfjqrrgpbcpaarsrg6ykwi

Photometric Stereo with Area Lights for Lambertian Surfaces

Jiangbin Gan, Thorsten Thormählen
2021 European Conference on Visual Media Production  
This paper presents a photometric stereo technique that uses area lights for normal recovery and 3D geometry reconstruction of midsized objects.  ...  Our synthetic and real-world experiments show that area lights are applicable for photometric stereo at the cost of an increased computational effort.  ...  Figure 6 : Comparison between WGP and our approach for a Buddha head.  ... 
doi:10.1145/3485441.3485651 fatcat:n5xb4wr3pvb4jdmxxvzah6ihoy

Integrated 3D display and imaging using dual purpose passive screen and head-mounted projectors and camera

Shoaib R. Soomro, Hakan Urey
2018 Optics Express  
The second layer is an imaging surface made up of an array of curved mirrors, which form the perspective views of the scene captured by a head-mounted camera.  ...  The real-time implementation is demonstrated by displaying stereo-3D content providing high brightness (up to 240 cd/m 2 ) and low crosstalk (<4%), while 3D image capture is demonstrated by performing  ...  Acknowledgment We would like to thank Kaan Akşit and Osman Eldeş for helpful discussions on computational image reconstruction.  ... 
doi:10.1364/oe.26.001161 pmid:29401993 fatcat:djy3jt2lv5hl5heoiwq2mj4a2e

Low-cost 360 stereo photography and video capture

Kevin Matzen, Michael F. Cohen, Bryce Evans, Johannes Kopf, Richard Szeliski
2017 ACM Transactions on Graphics  
Recent stereoscopic capture rigs involve placing many cameras in a ring and synthesizing an omni-directional stereo panorama enabling a user to look around to explore the scene in stereo.  ...  We have conducted a user study to better understand what kinds of geometric processing are necessary for a pleasant viewing experience.  ...  DISCUSSION AND FUTURE WORK We have demonstrated that two low-cost 360 • × 180 • cameras can capture compelling imagery for stereo viewing in a head-mounted display, despite the fact that the effective  ... 
doi:10.1145/3072959.3073645 fatcat:3w2fbxymzjffvjzwljhbwv7ozm

Imaging Geometry for Concentric Mosaics [article]

G. C. Watson, N. Vaughan, M. W. Wright
2000 Eurographics State of the Art Reports  
We show how this improved capture geometry can be employed in a head tracked display to produce a display that resembles a virtual window through which a captured environment can be viewed.  ...  Image-based models of environments can be captured with the use of a rotating video camera.  ...  The authors would like to acknowledge the assistance of Sharp Laboratories of Europe for the loan of equipment for this project, and the UK Engineering and Physical Science Research Council for funding  ... 
doi:10.2312/egs.20001011 fatcat:tyvq3tl5w5bdhd5kz3ic2e2iji

Fusing Multiview and Photometric Stereo for 3D Reconstruction under Uncalibrated Illumination

Chenglei Wu, Yebin Liu, Qionghai Dai, Bennett Wilburn
2011 IEEE Transactions on Visualization and Computer Graphics  
We propose a method to obtain a complete and accurate 3D model from multiview images captured under a variety of unknown illuminations.  ...  Surface normals are initialized using a multi-illumination multiview stereo algorithm, then refined using a robust alternating optimization method based on the ' 1 metric.  ...  The dome system is a hemisphere 6 m in diameter, with 20 low-speed FLEA2 cameras (30 fps) mounted on a ring roughly at head height. 290 Luxeon K2 LEDs are spread evenly over the whole hemisphere.  ... 
doi:10.1109/tvcg.2010.224 pmid:21659677 fatcat:lk3xsxdbajb3vkjpqpohp26taa

Ear-to-ear Capture of Facial Intrinsics [article]

Alassane Seck, William A. P. Smith, Arnaud Dessein, Bernard Tiddeman, Hannah Dee, Abhishek Dutta
2016 arXiv   pre-print
We use uncalibrated multiview stereo to estimate a coarse base mesh to which the photometric views are registered.  ...  We overcome the problem of having a single photometric viewpoint by capturing in multiple poses.  ...  ACKNOWLEDGMENTS We are grateful to Hadi Dahlan for assistance with data collection and to Fufu Fang for assistance with lightstage calibration and programming.  ... 
arXiv:1609.02368v1 fatcat:ir7aynfoybamjpmsfpszheux6m

Translational photometric alignment of single-view image sequences

Adam P. Harrison, Dileepan Joseph
2012 Computer Vision and Image Understanding  
Typically, photometric stereo requires an image sequence of an object under the same viewpoint but with differing illumination directions.  ...  Photometric stereo is a well-established method to estimate surface normals of an object. When coupled with depth-map estimation, it can be used to reconstruct an object's height field.  ...  For instance, as this paper will demonstrate, when capturing faces a human subject may move his or her head enough to affect photometric stereo performance.  ... 
doi:10.1016/j.cviu.2012.01.005 fatcat:h6vncfqk7zfdvls3yhuovqocdi

Face Shape and Reflectance Acquisition using a Multispectral Light Stage [article]

Abhishek Dutta
2011 arXiv   pre-print
stereo based performance geometry capture methods.  ...  Using the same radiance equations, we explore a Quadratic Programming (QP) based algorithm for correction of surface normals obtained using spherical gradient photometric stereo.  ...  Real Time Performance Capture The real time facial geometry of a dynamic performance can be captured using the spherical gradient photometric stereo based performance capture and photometric alignment  ... 
arXiv:1105.3617v1 fatcat:aulcfpxqubh5lcwfdspwyzomty

Photometric Stereo for Dynamic Surface Orientations [chapter]

Hyeongwoo Kim, Bennett Wilburn, Moshe Ben-Ezra
2010 Lecture Notes in Computer Science  
We present a photometric stereo method for non-rigid objects of unknown and spatially varying materials.  ...  We demonstrate the system's performance by computing surface orientations for several different moving, deforming objects.  ...  Photometric stereo results for several deforming objects verify the performance of the system. Background Although the literature on shape capture of deforming objects is vast, Nehab et al.  ... 
doi:10.1007/978-3-642-15549-9_5 fatcat:boeluocucrcajavrrtcdokaohu

A Morphable Face Albedo Model [article]

William A.P. Smith, Alassane Seck, Hannah Dee, Bernard Tiddeman, Joshua Tenenbaum, Bernhard Egger
2020 arXiv   pre-print
In this paper, we bring together two divergent strands of research: photometric face capture and statistical 3D face appearance modelling.  ...  We propose a novel lightstage capture and processing pipeline for acquiring ear-to-ear, truly intrinsic diffuse and specular albedo maps that fully factor out the effects of illumination, camera and geometry  ...  We acknowledge Abhishek Dutta for the original design and construction of our light stage. We thank Timo Bolkart for registering our data with the FLAME topology.  ... 
arXiv:2004.02711v2 fatcat:bxeaepoe4rdlrezmo3cd3owf6a

ICWall

T. v. d. Schaaf, D. M. Germans, M. Koutek, H. E. Bal
2006 Proceedings of the 2006 ACM international conference on Virtual reality continuum and its applications - VRCIA '06  
We demonstrate such a stereo-calibrated tiled display in action and we present recommendations for using this system to overcome remaining issues.  ...  Recent developments in the fields of parallel rendering and high resolution tiled displays have made it possible to apply these technologies to build large and scalable stereo displays for use in Virtual  ...  Acknowledgements This work was carried out in the context of the Virtual Laboratory for e-Science project (www.vl-e.nl).  ... 
doi:10.1145/1128923.1128972 dblp:conf/vrcai/SchaafGKB06 fatcat:xmb27qjcujhypdakxez5cozfcu

SYSTEM DESIGN, CALIBRATION AND PERFORMANCE ANALYSIS OF A NOVEL 360° STEREO PANORAMIC MOBILE MAPPING SYSTEM

S. Blaser, S. Nebiker, S. Cavegn
2017 ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
Furthermore, we automatically reconstructed a 3D city model of our study area by employing all captured and georeferenced mobile mapping imagery.  ...  By using two 360° panorama cameras tilted forward and backward in combination with conventional forward and backward looking stereo camera systems, we achieve a full 360° multi-stereo coverage.  ...  ACKNOWLEDGEMENTS This work was financially supported by the Swiss Commission for Technology and Innovation CTI as part of the infraVIS project that was performed in collaboration with iNovitas AG.  ... 
doi:10.5194/isprs-annals-iv-1-w1-207-2017 fatcat:hamhvhd5knhtxbr5zeg3rf3cpu

Effective Backscatter Approximation for Photometry in Murky Water [article]

Chourmouzios Tsiotsios, Maria E. Angelopoulou, Andrew J. Davison, Tae-Kyun Kim
2016 arXiv   pre-print
Shading-based approaches like Photometric Stereo assume that the image formation model can be effectively optimized for the scene normals. However, in murky water this is a very challenging problem.  ...  Our backscatter approximation method facilitates imaging and scene reconstruction in murky water when the illumination is artificial as in Photometric Stereo.  ...  We are very grateful to Underwater Systems and Technologies Laboratory (LSTS) and OceanScan in Porto for the access to the ROV and the help with the port-water experiments.  ... 
arXiv:1604.08789v1 fatcat:wiibiwumczgj7ht7v6ofaxtlou
« Previous Showing results 1 — 15 out of 668 results