Large-scale Codec Avatars: The Unreasonable Effectiveness of Large-scale Avatar Pretraining.

Carsten Stoll Max Planck Institute for Informatics, Saarbrücken, Germany http://www.mpi-sb.mpg.de/~stoll/ https://orcid.org/0000-0002-0119-4340

Junxuan Li Rawal Khirodkar Chengan He Zhongshi Jiang Giljoo Nam Lingchen Yang Jihyun Lee Egor Zakharov Zhaoen Su Rinat Abdrashitov Yuan Dong Julieta Martinez 0001 Kai Li 0016 Qingyang Tan Takaaki Shiratori Matthew Hu Peihong Guo Xuhua Huang Ariyan Zarei Marco Pesavento Yichen Xu He Wen 0001 Teng Deng Wyatt Borsos Anjali Thakrar Jean-Charles Bazin Carsten Stoll Ginés Hidalgo James Booth Lucy Wang Xiaowen Ma Yu Rong Sairanjith Thalanki Chen Cao 0001 Christian Häne Abhishek Kar Sofien Bouaziz Jason M. Saragih Yaser Sheikh Shunsuke Saito Large-scale Codec Avatars: The Unreasonable Effectiveness of Large-scale Avatar Pretraining. 2026 April abs/2604.02320 CoRR https://doi.org/10.48550/arXiv.2604.02320 db/journals/corr/corr2604.html#abs-2604-02320 streams/journals/corr

Aaron Ferguson Ahmed A. A. Osman Berta Bescós Carsten Stoll Christopher D. Twigg Christoph Lassner David Otte Eric Vignola Fabian Prada Federica Bogo Igor Santesteban Javier Romero 0002 Jenna Zarate Jeongseok Lee Jinhyung Park Jinlong Yang John Doublestein Kishore Venkateshan Kris Kitani Ladislav Kavan Marco Dal Farra Matthew Hu Matthew Cioffi Michael Fabris Michael Ranieri Mohammad Modarres Petr Kadlecek Rawal Khirodkar Rinat Abdrashitov Romain Prévost Roman Rajbhandari Ronald Mallet Russell Pearsall Sandy Kao Sanjeev Kumar Scott Parrish Shoou-I Yu Shunsuke Saito Takaaki Shiratori Te-Li Wang Tony Tung Yichen Xu Yuan Dong Yuhua Chen Yuanlu Xu Yuting Ye Zhongshi Jiang MHR: Momentum Human Rig. 2025 November abs/2511.15586 CoRR https://doi.org/10.48550/arXiv.2511.15586 db/journals/corr/corr2511.html#abs-2511-15586 streams/journals/corr

Nicola Garau Giulia Martinelli Niccolò Bisagno Denis Tomè Carsten Stoll EPOCH: Jointly Estimating the 3D Pose of Cameras and Humans. 1-18 2024 ECCV Workshops (13) https://doi.org/10.1007/978-3-031-91575-8_1 conf/eccv/2024-w13 db/conf/eccv/eccv2024-w13.html#GarauMBTS24 streams/conf/eccv Shashank Tripathi Omid Taheri Christoph Lassner Michael J. Black Daniel Holden Carsten Stoll HUMOS: Human Motion Model Conditioned on Body Shape. 133-152 2024 ECCV (16) https://doi.org/10.1007/978-3-031-72640-8_8 conf/eccv/2024-16 db/conf/eccv/eccv2024-16.html#TripathiTLBHS24 streams/conf/eccv Salvador Medina Sarah L. Taylor Carsten Stoll Gareth Edwards Alex Hauptmann 0001 Shinji Watanabe 0001 Iain A. Matthews PhISANet: Phonetically Informed Speech Animation Network. 8225-8229 2024 ICASSP https://doi.org/10.1109/ICASSP48485.2024.10448411 conf/icassp/2024 db/conf/icassp/icassp2024.html#MedinaTSE00M24

Tom Wehrbein Bodo Rosenhahn Iain A. Matthews Carsten Stoll Personalized 3D Human Pose and Shape Refinement. 2024 abs/2403.11634 CoRR https://doi.org/10.48550/arXiv.2403.11634 db/journals/corr/corr2403.html#abs-2403-11634

Yi Hua Christoph Lassner Carsten Stoll Iain A. Matthews fNeRF: High Quality Radiance Fields from Practical Cameras. 2024 abs/2406.10633 CoRR https://doi.org/10.48550/arXiv.2406.10633 db/journals/corr/corr2406.html#abs-2406-10633 streams/journals/corr

Nicola Garau Giulia Martinelli Niccolò Bisagno Denis Tomè Carsten Stoll EPOCH: Jointly Estimating the 3D Pose of Cameras and Humans. 2024 abs/2406.19726 CoRR https://doi.org/10.48550/arXiv.2406.19726 db/journals/corr/corr2406.html#abs-2406-19726 streams/journals/corr

Shashank Tripathi Omid Taheri Christoph Lassner Michael J. Black Daniel Holden Carsten Stoll HUMOS: Human Motion Model Conditioned on Body Shape. 2024 abs/2409.03944 CoRR https://doi.org/10.48550/arXiv.2409.03944 db/journals/corr/corr2409.html#abs-2409-03944 streams/journals/corr

Tom Wehrbein Bodo Rosenhahn Iain A. Matthews Carsten Stoll Personalized 3D Human Pose and Shape Refinement. 4191-4201 2023 ICCV (Workshops) https://doi.org/10.1109/ICCVW60793.2023.00453 conf/iccvw/2023 db/conf/iccvw/iccvw2023.html#WehrbeinRMS23 Salvador Medina Denis Tomè Carsten Stoll Mark Tiede Kevin Munhall Alex Hauptmann 0001 Iain A. Matthews Speech Driven Tongue Animation. 20374-20384 2022 CVPR https://doi.org/10.1109/CVPR52688.2022.01976 conf/cvpr/2022 db/conf/cvpr/cvpr2022.html#MedinaTSTM0M22 Amit Raj Julian Tanke James Hays Minh Vo Carsten Stoll Christoph Lassner ANR: Articulated Neural Rendering for Virtual Avatars. 3722-3731 2021 CVPR https://openaccess.thecvf.com/content/CVPR2021/html/Raj_ANR_Articulated_Neural_Rendering_for_Virtual_Avatars_CVPR_2021_paper.html https://doi.org/10.1109/CVPR46437.2021.00372 conf/cvpr/2021 db/conf/cvpr/cvpr2021.html#RajTHVSL21 Edgar Tretschk Ayush Tewari Vladislav Golyanik Michael Zollhöfer Carsten Stoll Christian Theobalt PatchNets: Patch-Based Generalizable Deep Implicit 3D Shape Representations. 293-309 2020 ECCV (16) https://doi.org/10.1007/978-3-030-58517-4_18 conf/eccv/2020-16 db/conf/eccv/eccv2020-16.html#TretschkTGZST20 Tiancheng Zhi Christoph Lassner Tony Tung Carsten Stoll Srinivasa G. Narasimhan Minh Vo TexMesh: Reconstructing Detailed Human Texture and Geometry from RGB-D Video. 492-509 2020 ECCV (10) https://doi.org/10.1007/978-3-030-58607-2_29 conf/eccv/2020-10 db/conf/eccv/eccv2020-10.html#ZhiLTSNV20

Tiancheng Zhi Christoph Lassner Tony Tung Carsten Stoll Srinivasa G. Narasimhan Minh Vo TexMesh: Reconstructing Detailed Human Texture and Geometry from RGB-D Video. 2020 abs/2008.00158 CoRR https://arxiv.org/abs/2008.00158 db/journals/corr/corr2008.html#abs-2008-00158

Edgar Tretschk Ayush Tewari Vladislav Golyanik Michael Zollhöfer Carsten Stoll Christian Theobalt PatchNets: Patch-Based Generalizable Deep Implicit 3D Shape Representations. 2020 abs/2008.01639 CoRR https://arxiv.org/abs/2008.01639 db/journals/corr/corr2008.html#abs-2008-01639

Amit Raj Julian Tanke James Hays Minh Vo Carsten Stoll Christoph Lassner ANR: Articulated Neural Rendering for Virtual Avatars. 2020 abs/2012.12890 CoRR https://arxiv.org/abs/2012.12890 db/journals/corr/corr2012.html#abs-2012-12890

Ahmed Elhayek Carsten Stoll Kwang In Kim Christian Theobalt Outdoor Human Motion Capture by Simultaneous Optimization of Pose and Camera Parameters. 86-98 2015 34 Comput. Graph. Forum 6 https://doi.org/10.1111/cgf.12519 db/journals/cgf/cgf34.html#ElhayekSKT15

Guannan Li Chenglei Wu Carsten Stoll Yebin Liu Kiran Varanasi Qionghai Dai Christian Theobalt Capturing Relightable Human Performances under General Uncontrolled Illumination. 275-284 2013 32 Comput. Graph. Forum 2 https://doi.org/10.1111/cgf.12047 db/journals/cgf/cgf32.html#LiWSLVDT13

Yebin Liu Juergen Gall Carsten Stoll Qionghai Dai Hans-Peter Seidel Christian Theobalt Markerless Motion Capture of Multiple Characters Using Multiview Image Segmentation. 2720-2735 2013 35 IEEE Trans. Pattern Anal. Mach. Intell. 11 https://doi.org/10.1109/TPAMI.2013.47 http://doi.ieeecomputersociety.org/10.1109/TPAMI.2013.47 https://www.wikidata.org/entity/Q44843561 db/journals/pami/pami35.html#LiuGSDST13

Chenglei Wu Carsten Stoll Levi Valgaerts Christian Theobalt On-set performance capture of multiple actors with a stereo camera. 161:1-161:11 2013 32 ACM Trans. Graph. 6 https://doi.org/10.1145/2508363.2508418 db/journals/tog/tog32.html#WuSVT13

Christian Richardt Carsten Stoll Neil A. Dodgson Hans-Peter Seidel Christian Theobalt Coherent Spatiotemporal Filtering, Upsampling and Rendering of RGBZ Videos. 247-256 2012 31 Comput. Graph. Forum 2pt1 https://doi.org/10.1111/j.1467-8659.2012.03003.x https://www.wikidata.org/entity/Q59750907 db/journals/cgf/cgf31.html#RichardtSDST12

Ahmed Elhayek Carsten Stoll Nils Hasler Kwang In Kim Hans-Peter Seidel Christian Theobalt Spatio-temporal motion tracking with unsynchronized cameras. 1870-1877 2012 CVPR https://doi.org/10.1109/CVPR.2012.6247886 https://doi.ieeecomputersociety.org/10.1109/CVPR.2012.6247886 conf/cvpr/2012 db/conf/cvpr/cvpr2012.html#ElhayekSHKST12 Ahmed Elhayek Carsten Stoll Kwang In Kim Hans-Peter Seidel Christian Theobalt Feature-Based Multi-video Synchronization with Subframe Accuracy. 266-275 2012 DAGM/OAGM Symposium https://doi.org/10.1007/978-3-642-32717-9_27 conf/dagm/2012 db/conf/dagm/dagm2012.html#ElhayekSKST12

Feng Xu 0005 Yebin Liu Carsten Stoll James Tompkin 0001 Gaurav Bharaj Qionghai Dai Hans-Peter Seidel Jan Kautz Christian Theobalt Video-based characters: creating new human performances from a multi-view video database. 32 2011 30 ACM Trans. Graph. 4 https://doi.org/10.1145/2010324.1964927 https://doi.org/10.1145/1964921.1964927 db/journals/tog/tog30.html#XuLSTBDSKT11

Yebin Liu Carsten Stoll Juergen Gall Hans-Peter Seidel Christian Theobalt Markerless motion capture of interacting characters using multi-view image segmentation. 1249-1256 2011 CVPR https://doi.org/10.1109/CVPR.2011.5995424 https://doi.ieeecomputersociety.org/10.1109/CVPR.2011.5995424 conf/cvpr/2011 db/conf/cvpr/cvpr2011.html#LiuSGST11 Carsten Stoll Nils Hasler Juergen Gall Hans-Peter Seidel Christian Theobalt Fast articulated motion tracking using a sums of Gaussians body model. 951-958 2011 ICCV https://doi.org/10.1109/ICCV.2011.6126338 https://doi.ieeecomputersociety.org/10.1109/ICCV.2011.6126338 conf/iccv/2011 db/conf/iccv/iccv2011.html#StollHGST11

Carsten Stoll Juergen Gall Edilson de Aguiar Sebastian Thrun Christian Theobalt Video-based reconstruction of animatable human characters. 139 2010 29 ACM Trans. Graph. 6 https://doi.org/10.1145/1882261.1866161 https://doi.org/10.1145/1866158.1866161 db/journals/tog/tog29.html#StollGATT10

Levi Valgaerts Andrés Bruhn Henning Zimmer Joachim Weickert Carsten Stoll Christian Theobalt Joint Estimation of Motion, Structure and Geometry from Stereo Sequences. 568-581 2010 ECCV (4) https://doi.org/10.1007/978-3-642-15561-1_41 conf/eccv/2010-4 db/conf/eccv/eccv2010-4.html#ValgaertsBZWST10 Christian Theobalt Edilson de Aguiar Carsten Stoll Hans-Peter Seidel Sebastian Thrun Performance Capture from Multi-View Video. 127-149 2010 Image and Geometry Processing for 3-D Cinematography https://doi.org/10.1007/978-3-642-12392-4_6 books/sp/cinema2010 db/books/collections/cinema2010.html#TheobaltASST10 Carsten Stoll Template based shape processing. 2009 Saarland University http://scidok.sulb.uni-saarland.de/volltexte/2010/2965/ https://nbn-resolving.org/urn:nbn:de:bsz:291-scidok-29653 https://d-nb.info/1002336538

Nils Hasler Carsten Stoll Bodo Rosenhahn Thorsten Thormählen Hans-Peter Seidel Estimating body shape of dressed humans. 211-216 2009 33 Comput. Graph. 3 https://doi.org/10.1016/j.cag.2009.03.026 db/journals/cg/cg33.html#HaslerSRTS09

Nils Hasler Carsten Stoll Martin Sunkel Bodo Rosenhahn Hans-Peter Seidel A Statistical Model of Human Pose and Body Shape. 337-346 2009 28 Comput. Graph. Forum 2 https://doi.org/10.1111/j.1467-8659.2009.01373.x db/journals/cgf/cgf28.html#HaslerSSRS09

Juergen Gall Carsten Stoll Edilson de Aguiar Christian Theobalt Bodo Rosenhahn Hans-Peter Seidel Motion capture using joint skeleton tracking and surface estimation. 1746-1753 2009 CVPR https://doi.org/10.1109/CVPR.2009.5206755 https://doi.org/10.1109/CVPRW.2009.5206755 https://doi.ieeecomputersociety.org/10.1109/CVPR.2009.5206755 conf/cvpr/2009 db/conf/cvpr/cvpr2009.html#GallSATRS09

Edilson de Aguiar Carsten Stoll Christian Theobalt Naveed Ahmed 0001 Hans-Peter Seidel Sebastian Thrun Performance capture from sparse multi-view video. 2008 27 ACM Trans. Graph. 3 https://doi.org/10.1145/1360612.1360697 https://doi.org/10.1145/1399504.1360697 db/journals/tog/tog27.html#AguiarSTAST08 98

Edilson de Aguiar Christian Theobalt Carsten Stoll Hans-Peter Seidel Marker-less Deformable Mesh Tracking for Human Shape and Motion Capture. 2007 conf/cvpr/2007 CVPR https://doi.org/10.1109/CVPR.2007.383296 https://doi.ieeecomputersociety.org/10.1109/CVPR.2007.383296 db/conf/cvpr/cvpr2007.html#AguiarTSS07 Edilson de Aguiar Christian Theobalt Carsten Stoll Hans-Peter Seidel Marker-Less 3D Feature Tracking for Mesh-Based Human Motion Capture. 1-15 2007 conf/humo/2007 Workshop on Human Motion https://doi.org/10.1007/978-3-540-75703-0_1 db/conf/humo/humo2007.html#AguiarTSS07 Edilson de Aguiar Christian Theobalt Carsten Stoll Hans-Peter Seidel Rapid Animation of Laser-scanned Humans. 223-226 2007 VR https://doi.org/10.1109/VR.2007.352486 https://doi.ieeecomputersociety.org/10.1109/VR.2007.352486 conf/vr/2007 db/conf/vr/vr2007.html#AguiarTSS07 Carsten Stoll Hans-Peter Seidel Marc Alexa BSP Shapes. 42 2006 conf/smi/2006 SMI https://doi.org/10.1109/SMI.2006.5 https://doi.ieeecomputersociety.org/10.1109/SMI.2006.5 db/conf/smi/smi2006.html#StollSA06 Carsten Stoll Zachi Karni Christian Rössl Hitoshi Yamauchi Hans-Peter Seidel Template Deformation for Point Cloud Fitting. 27-35 2006 PBG@SIGGRAPH https://doi.org/10.2312/SPBG/SPBG06/027-035 conf/spbg/2006 db/conf/spbg/spbg2006.html#StollKRYS06 Carsten Stoll Stefan Gumhold Hans-Peter Seidel Visualization with stylized line primitives. 695-702 2005 conf/visualization/2005 IEEE Visualization https://doi.org/10.1109/VISUAL.2005.1532859 https://doi.ieeecomputersociety.org/10.1109/VIS.2005.124 db/conf/visualization/visualization2005.html#StollGS05 Marc Alexa Tobias Klug Carsten Stoll Direction Fields over Point-Sampled Geometry. 2003 conf/wscg/2003 WSCG http://wscg.zcu.cz/wscg2003/Papers_2003/I03.pdf db/conf/wscg/wscg2003.html#AlexaKS03 Rinat Abdrashitov Edilson de Aguiar Naveed Ahmed 0001 Marc Alexa Jean-Charles Bazin Berta Bescós Gaurav Bharaj Niccolò Bisagno Michael J. Black Federica Bogo James Booth Wyatt Borsos Sofien Bouaziz Andrés Bruhn Chen Cao 0001 Yuhua Chen Matthew Cioffi Qionghai Dai Teng Deng Neil A. Dodgson Yuan Dong John Doublestein Gareth Edwards Ahmed Elhayek Michael Fabris Marco Dal Farra Aaron Ferguson Juergen Gall Nicola Garau Vladislav Golyanik Stefan Gumhold Peihong Guo Christian Häne Nils Hasler Alex Hauptmann 0001 James Hays Chengan He Ginés Hidalgo Daniel Holden Matthew Hu Yi Hua Xuhua Huang Zhongshi Jiang Petr Kadlecek Sandy Kao Abhishek Kar Zachi Karni Jan Kautz Ladislav Kavan Rawal Khirodkar Kwang In Kim Kris Makoto KitaniKris Kitani Tobias Klug Sanjeev Kumar Christoph Lassner Jeongseok Lee Jihyun Lee Guannan Li Junxuan Li Kai Li 0016 Yebin Liu Xiaowen Ma Ronald Mallet Giulia Martinelli Julieta Martinez 0001 Iain A. Matthews Salvador Medina Mohammad Modarres Kevin Munhall Giljoo Nam Srinivasa G. Narasimhan Ahmed A. A. Osman David Otte Jinhyung Park Scott Parrish Russell Pearsall Marco Pesavento Fabian Prada Romain Prévost Amit Raj Roman Rajbhandari Michael Ranieri Christian Richardt Javier Romero 0002 Yu Rong Bodo Rosenhahn Christian Rössl Shunsuke Saito Igor Santesteban Jason M. Saragih Hans-Peter Seidel Yaser Sheikh Takaaki Shiratori Zhaoen Su Martin Sunkel Omid Taheri Qingyang Tan Julian Tanke Sarah L. Taylor Ayush Tewari Anjali Thakrar Sairanjith Thalanki Christian Theobalt Thorsten Thormählen Sebastian Thrun Mark K. TiedeMark Tiede Denis Tomè James Tompkin 0001 Edith TretschkEdgar Tretschk Shashank Tripathi Tony Tung Christopher D. Twigg Levi Valgaerts Kiran Varanasi Kishore Venkateshan Eric Vignola Minh Vo Lucy Wang Te-Li Wang Shinji Watanabe 0001 Tom Wehrbein Joachim Weickert He Wen 0001 Chenglei Wu Feng Xu 0005 Yichen Xu Yuanlu Xu Hitoshi Yamauchi Jinlong Yang Lingchen Yang Yuting Ye Shoou-I Yu Egor Zakharov Jenna Zarate Ariyan Zarei Tiancheng Zhi Henning Zimmer Michael Zollhöfer