Filters








16,087 Hits in 19.3 sec

NRST: Non-rigid Surface Tracking from Monocular Video [article]

Marc Habermann, Weipeng Xu, Helge Rhodin, Michael Zollhoefer, Gerard Pons-Moll, Christian Theobalt
2021 arXiv   pre-print
We propose an efficient method for non-rigid surface tracking from monocular RGB videos.  ...  We formulate the per-frame registration as an optimization problem that includes a novel texture term specifically tailored towards tracking objects with uniform texture but fine-scale structure, such  ...  Introduction In this paper, we propose NRST, an efficient method for non-rigid surface tracking from monocular RGB videos.  ... 
arXiv:2107.02407v2 fatcat:v5f2x27lazhg3cgbfk3qnqzyyi

NRST: Non-rigid Surface Tracking from Monocular Video [chapter]

Marc Habermann, Weipeng Xu, Helge Rhodin, Michael Zollhöfer, Gerard Pons-Moll, Christian Theobalt
2019 Lecture Notes in Computer Science  
We propose an efficient method for non-rigid surface tracking from monocular RGB videos.  ...  We formulate the per-frame registration as an optimization problem that includes a novel texture term specifically tailored towards tracking objects with uniform texture but fine-scale structure, such  ...  Introduction In this paper, we propose NRST, an efficient method for non-rigid surface tracking from monocular RGB videos.  ... 
doi:10.1007/978-3-030-12939-2_23 fatcat:utfyyegyxzdhxp76rjob4qbq3e

Model-based Outdoor Performance Capture [article]

Nadia Robertini, Dan Casas, Helge Rhodin, Hans-Peter Seidel, Christian Theobalt
2016 arXiv   pre-print
Starting from a template of the actor model, we introduce a new unified implicit representation for both, articulated skeleton tracking and nonrigid surface shape refinement.  ...  Particularly for surface shape refinement we propose a new combination of 3D Gaussians designed to align the projected model with likely silhouette contours without explicit segmentation or edge detection  ...  Acknowledgements We thank all reviewers for their valuable feedback and The Foundry for license support. This research was funded by the ERC Starting Grant project CapReal (335545).  ... 
arXiv:1610.06740v1 fatcat:cxjg5taymjhzvliqgglynueene

General Automatic Human Shape and Motion Capture Using Volumetric Contour Cues [article]

Helge Rhodin, Nadia Robertini, Dan Casas, Christian Richardt, Hans-Peter Seidel, Christian Theobalt
2016 arXiv   pre-print
Our method uses a new image formation model with analytic visibility and analytically differentiable alignment energy. For reconstruction, 3D body shape is approximated as Gaussian density field.  ...  Markerless motion capture algorithms require a 3D body with properly personalized skeleton dimension and/or body shape and appearance to successfully track a person.  ...  and Leonid Sigal for providing their data and test sequences, The Foundry for license support, and all our actors.  ... 
arXiv:1607.08659v2 fatcat:ye37f3vy7jgp5fsvekw7mcwe7m

STAR3D: Simultaneous Tracking and Reconstruction of 3D Objects Using RGB-D Data

Carl Yuheng Ren, Victor Prisacariu, David Murray, Ian Reid
2013 2013 IEEE International Conference on Computer Vision  
We introduce a probabilistic framework for simultaneous tracking and reconstruction of 3D rigid objects using an RGB-D camera.  ...  Surface and background appearance models are learned online, leading to robust tracking in the presence of heavy occlusion and outliers.  ...  (Right): Graphical model of our generative model for tracking and reconstruction.  ... 
doi:10.1109/iccv.2013.197 dblp:conf/iccv/RenPMR13 fatcat:3dywhvyb4zg5tg2afkxzvjfgw4

Cage-Based Tracking for Performance Animation [chapter]

Yann Savoye, Jean-Sébastien Franco
2011 Lecture Notes in Computer Science  
We propose the first algorithm for performing cage-based tracking across time for vision and virtual reality applications.  ...  Highly-detailed performance animations are easier to obtain using existing multiple views platforms, markerless capture and 3D laser scanner.  ...  A major challenge is to exhibit an efficient framework to achieve plausible boneless tracking that produces pleasing deformations, preserves the global appearance of the surface and offers flexible reusable  ... 
doi:10.1007/978-3-642-19318-7_47 fatcat:worend3tprevlbv5g5rbcmu4gi

LiveCap: Real-time Human Performance Capture from Monocular Video [article]

Marc Habermann and Weipeng Xu and Michael Zollhoefer and Gerard Pons-Moll and Christian Theobalt
2019 arXiv   pre-print
In the first stage, a skinned template model is jointly fitted to background subtracted input video, 2D and 3D skeleton joint positions found using a deep neural network, and a set of sparse facial landmark  ...  In the second stage, dense non-rigid 3D deformations of skin and even loose apparel are captured based on a novel real-time capable algorithm for non-rigid tracking using dense photometric and silhouette  ...  reconstruct an actor model in a preprocessing step.  ... 
arXiv:1810.02648v3 fatcat:ijfxnvdczzc6jh2gpywnmde47y

Temporally Coherent General Dynamic Scene Reconstruction [article]

Armin Mustafa, Marco Volino, Hansung Kim, Jean-Yves Guillemaut, Adrian Hilton
2020 arXiv   pre-print
This paper demonstrates unsupervised reconstruction of complete temporally coherent 4D scene models with improved non-rigid object segmentation and shape reconstruction and its application to free-viewpoint  ...  Contributions of the work are: An automatic method for initial coarse reconstruction to initialize joint estimation; Sparse-to-dense temporal correspondence integrated with joint multi-view segmentation  ...  Smoothness term: This term is inspired by [23] and it ensures the depth labels vary smoothly within the object reducing noise and peaks in the reconstructed surface.  ... 
arXiv:1907.08195v2 fatcat:pcjsowtlj5ejdpnidxerof2kcy

Interactive Visual Hull Refinement for Specular and Transparent Object Surface Reconstruction

Xinxin Zuo, Chao Du, Sen Wang, Jiangbin Zheng, Ruigang Yang
2015 2015 IEEE International Conference on Computer Vision (ICCV)  
Based on the two core algorithms, we have developed an interactive system for 3D modeling.  ...  In this paper we present a method of using standard multi-view images for 3D surface reconstruction of non-Lambertian objects.  ...  The second and third term enforce the smoothness constraints with δd p stands for the depth gradient.  ... 
doi:10.1109/iccv.2015.258 dblp:conf/iccv/ZuoDWZY15 fatcat:uxhftcy7l5gjxdwsz3egwlmoz4

Where Does It End? – Reasoning About Hidden Surfaces by Object Intersection Constraints [article]

Michael Strecke, Joerg Stueckler
2020 arXiv   pre-print
An object-level dynamic SLAM frontend detects, segments, tracks and maps dynamic objects in the scene.  ...  In this paper we propose Co-Section, an optimization-based approach to 3D dynamic scene reconstruction, which infers hidden shape information from intersection constraints.  ...  It detects, segments, tracks and 3D reconstructs the objects in local volumetric SDF representations.  ... 
arXiv:2004.04630v2 fatcat:xjogbxamarggddgrpg7xehakjm

RGB-D object modelling for object recognition and tracking

Johann Prankl, Aitor Aldoma, Alexander Svejda, Markus Vincze
2015 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)  
This work presents a flexible system to reconstruct 3D models of objects captured with an RGB-D sensor.  ...  In addition, the 3D models acquired by our system can be directly used by state-of-the-art object instance recognition and object tracking modules, providing object-perception capabilities to complex applications  ...  We also show how the reconstructed 3D models are effectively used for object instance recognition and 6-DoF pose estimation, as well as for object tracking with monocular cameras. II.  ... 
doi:10.1109/iros.2015.7353360 dblp:conf/iros/PranklASV15 fatcat:wv4b4egjebhjrcpm3m5ogix2ua

Hybrid modelling of non-rigid scenes from RGBD cameras

Charles Malleson, Jean-Yves Guillemaut, Adrian Hilton
2018 IEEE transactions on circuits and systems for video technology (Print)  
A hybrid representation is proposed which combines the advantages of prior surfel graph surface segmentation and modelling work with the higher-resolution surface reconstruction capability of volumetric  ...  to generate dense geometry, and (3) proposal of means for validation of the reconstructed 4D scene model against the input data and efficient storage of any unmodelled regions via residual depth maps.  ...  ACKNOWLEDGMENT This work was funded by the EU FP7 project SCENE and EPSRC Audio-Visual Media Platform Grant EP/PO22529/1.  ... 
doi:10.1109/tcsvt.2018.2863027 fatcat:ydefxrbxn5h75acnl33ektzv3u

Temporally Coherent 4D Reconstruction of Complex Dynamic Scenes

Armin Mustafa, Hansung Kim, Jean-Yves Guillemaut, Adrian Hilton
2016 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
This paper presents an approach for reconstruction of 4D temporally coherent models of complex dynamic scenes.  ...  This demonstrates reconstruction of complete temporally coherent 4D scene models with improved nonrigid object segmentation and shape reconstruction.  ...  Acknowledgements: This research was supported by the European Commission, FP7 Intelligent Management Platform for Advanced Real-time Media Processes project (grant 316564).  ... 
doi:10.1109/cvpr.2016.504 dblp:conf/cvpr/MustafaKGH16 fatcat:5iz2zxxs35hudkwnqo5hoftf3a

A Versatile Scene Model with Differentiable Visibility Applied to Generative Pose Estimation

Helge Rhodin, Nadia Robertini, Christian Richardt, Hans-Peter Seidel, Christian Theobalt
2015 2015 IEEE International Conference on Computer Vision (ICCV)  
Generative reconstruction methods compute the 3D configuration (such as pose and/or geometry) of a shape by optimizing the overlap of the projected 3D shape model with images.  ...  In contrast to previous methods, this yields smooth, analytically differentiable, and efficient to optimize pose similarity energies with rigorous occlusion handling, fewer local minima, and experimentally  ...  Acknowledgements We thank Oliver Klehm, Tobias Ritchel, Carsten Stoll and Nils Hasler for valuable discussions and feedback.  ... 
doi:10.1109/iccv.2015.94 dblp:conf/iccv/RhodinRRST15 fatcat:xjcrrczs6vealamjkri4rvwooa

A Versatile Scene Model with Differentiable Visibility Applied to Generative Pose Estimation [article]

Helge Rhodin, Nadia Robertini, Christian Richardt, Hans-Peter Seidel, Christian Theobalt
2016 arXiv   pre-print
Generative reconstruction methods compute the 3D configuration (such as pose and/or geometry) of a shape by optimizing the overlap of the projected 3D shape model with images.  ...  In contrast to previous methods, this yields smooth, analytically differentiable, and efficient to optimize pose similarity energies with rigorous occlusion handling, fewer local minima, and experimentally  ...  Acknowledgements We thank Oliver Klehm, Tobias Ritschel, Carsten Stoll and Nils Hasler for valuable discussions and feedback.  ... 
arXiv:1602.03725v1 fatcat:yjrtut2qp5fqfnmjxubmaputpi
« Previous Showing results 1 — 15 out of 16,087 results