@inproceedings{xue2026georelight,
  author       = {Yuxuan Xue and
                  Ruofan Liang and
                  Egor Zakharov and
                  Timur M. Bagautdinov and
                  Chen Cao and
                  Giljoo Nam and
                  Shunsuke Saito and
                  Gerard Pons{-}Moll and
                  \textbf{Javier Romero}},
  title        = {GeoRelight: Learning Joint Geometrical Relighting and Reconstruction
                  with Flexible Multi-Modal Diffusion Transformers},
  booktitle    = {{IEEE/CVF} Conference on Computer Vision and Pattern Recognition,
                  {CVPR} 2026, Denver, CO, USA, June 3-7, 2026},
  pages        = {29771--29780},
  publisher    = {Computer Vision Foundation},
  year         = {2026},
  url          = {https://openaccess.thecvf.com/content/CVPR2026/html/Xue\_GeoRelight\_Learning\_Joint\_Geometrical\_Relighting\_and\_Reconstruction\_with\_Flexible\_Multi-Modal\_CVPR\_2026\_paper.html},
}
@article{ferguson2026mhr,
  author       = {Aaron Ferguson and
                  Ahmed A. A. Osman and
                  Berta Besc{\'{o}}s and
                  Carsten Stoll and
                  Christopher D. Twigg and
                  Christoph Lassner and
                  David Otte and
                  Eric Vignola and
                  Fabian Prada and
                  Federica Bogo and
                  Igor Santesteban and
                  \textbf{Javier Romero} and
                  Jenna Zarate and
                  Jeongseok Lee and
                  Jinhyung Park and
                  Jinlong Yang and
                  John Doublestein and
                  Kishore Venkateshan and
                  Kris Kitani and
                  Ladislav Kavan and
                  Marco Dal Farra and
                  Matthew Hu and
                  Matthew Cioffi and
                  Michael Fabris and
                  Michael Ranieri and
                  Mohammad Modarres and
                  Petr Kadlecek and
                  Rawal Khirodkar and
                  Rinat Abdrashitov and
                  Romain Pr{\'{e}}vost and
                  Roman Rajbhandari and
                  Ronald Mallet and
                  Russell Pearsall and
                  Sandy Kao and
                  Sanjeev Kumar and
                  Scott Parrish and
                  Shoou{-}I Yu and
                  Shunsuke Saito and
                  Takaaki Shiratori and
                  Te{-}Li Wang and
                  Tony Tung and
                  Yichen Xu and
                  Yuan Dong and
                  Yuhua Chen and
                  Yuanlu Xu and
                  Yuting Ye and
                  Zhongshi Jiang},
  title        = {{MHR:} Momentum Human Rig},
  journal      = {CoRR},
  volume       = {abs/2511.15586},
  year         = {2025},
  url          = {https://doi.org/10.48550/arXiv.2511.15586},
  doi          = {10.48550/ARXIV.2511.15586},
  eprinttype   = {arXiv},
  eprint       = {2511.15586},
}
@inproceedings{park2025atlas,
  author       = {Jinhyung Park and
                  \textbf{Javier Romero} and
                  Shunsuke Saito and
                  Fabian Prada and
                  Takaaki Shiratori and
                  Yichen Xu and
                  Federica Bogo and
                  Shoou{-}I Yu and
                  Kris Kitani and
                  Rawal Khirodkar},
  title        = {{ATLAS:} Decoupling Skeletal and Shape Parameters for Expressive Parametric
                  Human Modeling},
  booktitle    = {{IEEE/CVF} International Conference on Computer Vision, {ICCV} 2025,
                  Honolulu, HI, USA, October 19-25, 2025},
  pages        = {6508--6518},
  publisher    = {{IEEE}},
  year         = {2025},
}
@inproceedings{kirschstein2025avat3r,
  author       = {Tobias Kirschstein and
                  \textbf{Javier Romero} and
                  Artem Sevastopolsky and
                  Matthias Nie{\ss}ner and
                  Shunsuke Saito},
  title        = {Avat3r: Large Animatable Gaussian Reconstruction Model for High-Fidelity
                  3D Head Avatars},
  booktitle    = {{IEEE/CVF} International Conference on Computer Vision, {ICCV} 2025,
                  Honolulu, HI, USA, October 19-25, 2025},
  pages        = {12089--12100},
  publisher    = {{IEEE}},
  year         = {2025},
  url          = {https://doi.org/10.1109/ICCV51701.2025.01124},
  doi          = {10.1109/ICCV51701.2025.01124},
}
@inproceedings{wang2025relightable,
  author       = {Shaofei Wang and
                  Tomas Simon and
                  Igor Santesteban and
                  Timur M. Bagautdinov and
                  Junxuan Li and
                  Vasu Agrawal and
                  Fabian Prada and
                  Shoou{-}I Yu and
                  Pace Nalbone and
                  Matt Gramlich and
                  Roman Lubachersky and
                  Chenglei Wu and
                  \textbf{Javier Romero} and
                  Jason M. Saragih and
                  Michael Zollh{\"{o}}fer and
                  Andreas Geiger and
                  Siyu Tang and
                  Shunsuke Saito},
  editor       = {Ginger Alford and
                  Hao (Richard) Zhang and
                  Adriana Schulz},
  title        = {Relightable Full-Body Gaussian Codec Avatars},
  booktitle    = {Proceedings of the Special Interest Group on Computer Graphics and
                  Interactive Techniques Conference, {SIGGRAPH} Conference Papers 2025,
                  Vancouver, BC, Canada, August 10-14, 2025},
  pages        = {146:1--146:12},
  publisher    = {{ACM}},
  year         = {2025},
}
@article{he20253dgh,
  author       = {Chengan He and
                  Junxuan Li and
                  Tobias Kirschstein and
                  Artem Sevastopolsky and
                  Shunsuke Saito and
                  Qingyang Tan and
                  \textbf{Javier Romero} and
                  Chen Cao and
                  Holly E. Rushmeier and
                  Giljoo Nam},
  title        = {3DGH: 3D Head Generation with Composable Hair and Face},
  journal      = {{ACM} Trans. Graph.},
  volume       = {44},
  number       = {4},
  pages        = {59:1--59:12},
  year         = {2025},
  url          = {https://doi.org/10.1145/3731211},
  doi          = {10.1145/3731211},
}
@inproceedings{wang2025fresa,
  author       = {Rong Wang and
                  Fabian Prada and
                  Ziyan Wang and
                  Zhongshi Jiang and
                  Chengxiang Yin and
                  Junxuan Li and
                  Shunsuke Saito and
                  Igor Santesteban and
                  \textbf{Javier Romero} and
                  Rohan Joshi and
                  Hongdong Li and
                  Jason M. Saragih and
                  Yaser Sheikh},
  title        = {{FRESA:} Feedforward Reconstruction of Personalized Skinned Avatars
                  from Few Images},
  booktitle    = {{IEEE/CVF} Conference on Computer Vision and Pattern Recognition,
                  {CVPR} 2025, Nashville, TN, USA, June 11-15, 2025},
  pages        = {281--291},
  publisher    = {Computer Vision Foundation / {IEEE}},
  year         = {2025},
  url          = {https://openaccess.thecvf.com/content/CVPR2025/html/Wang\_FRESA\_Feedforward\_Reconstruction\_of\_Personalized\_Skinned\_Avatars\_from\_Few\_Images\_CVPR\_2025\_paper.html},
  doi          = {10.1109/CVPR52734.2025.00035},
}
@inproceedings{martinez2025AVA256,
  author       = {Julieta Martinez and
                  Emily Kim and
                  \textbf{Javier Romero} and
                  Timur M. Bagautdinov and
                  Shunsuke Saito and
                  Shoou{-}I Yu and
                  Stuart Anderson and
                  Michael Zollh{\"{o}}fer and
                  Te{-}Li Wang and
                  Shaojie Bai and
                  Chenghui Li and
                  Shih{-}En Wei and
                  Rohan Joshi and
                  Wyatt Borsos and
                  Tomas Simon and
                  Jason M. Saragih and
                  Paul Theodosis and
                  Alexander Greene and
                  Anjani Josyula and
                  Silvio Maeta and
                  Andrew Jewett and
                  Simion Venshtain and
                  Christopher Heilman and
                  Yueh{-}Tung Chen and
                  Sidi Fu and
                  Mohamed Elshaer and
                  Tingfang Du and
                  Longhua Wu and
                  Shen{-}Chi Chen and
                  Kai Kang and
                  Michael Wu and
                  Youssef Emad and
                  Steven Longay and
                  Ashley Brewer and
                  Hitesh Shah and
                  James Booth and
                  Taylor Koska and
                  Kayla Haidle and
                  Matthew Andromalos and
                  Joanna Hsu and
                  Thomas Dauer and
                  Peter Selednik and
                  Timothy Godisart and
                  Scott Ardisson and
                  Matthew Cipperly and
                  Ben Humberston and
                  Lon Farr and
                  Bob Hansen and
                  Peihong Guo and
                  Dave Braun and
                  Steven Krenn and
                  He Wen and
                  Lucas Evans and
                  Natalia Fadeeva and
                  Matthew Stewart and
                  Gabriel Schwartz and
                  Divam Gupta and
                  Gyeongsik Moon and
                  Kaiwen Guo and
                  Yuan Dong and
                  Yichen Xu and
                  Takaaki Shiratori and
                  Fabian Prada and
                  Bernardo Pires and
                  Bo Peng and
                  Julia Buffalini and
                  Autumn Trimble and
                  Kevyn McPhail and
                  Melissa Schoeller and
                  Yaser Sheikh},
  editor       = {Amir Globersons and
                  Lester Mackey and
                  Danielle Belgrave and
                  Angela Fan and
                  Ulrich Paquet and
                  Jakub M. Tomczak and
                  Cheng Zhang},
  title        = {Codec Avatar Studio: Paired Human Captures for Complete, Driveable,
                  and Generalizable Avatars},
  booktitle    = {Advances in Neural Information Processing Systems 37: Annual Conference
                  on Neural Information Processing Systems 2024, NeurIPS 2024, Vancouver,
                  BC, Canada, December 10 - 15, 2024},
  year         = {2024},
  url          = {http://papers.nips.cc/paper\_files/paper/2024/hash/9712b78386cebdc3db7f1a48c2d20edb-Abstract-Datasets\_and\_Benchmarks\_Track.html},
}
@inproceedings{rasras2024ltt,
  author       = {Feisal Rasras and
                  Stanislav Pidhorskyi and
                  Tomas Simon and
                  Hallison Paz and
                  He Wen and
                  Jason M. Saragih and
                  \textbf{Javier Romero}},
  editor       = {Takeo Igarashi and
                  Ariel Shamir and
                  Hao (Richard) Zhang},
  title        = {The Lips, the Teeth, the tip of the Tongue: {LTT} Tracking},
  booktitle    = {{SIGGRAPH} Asia 2024 Conference Papers, {SA} 2024, Tokyo, Japan, December
                  3-6, 2024},
  pages        = {115:1--115:11},
  publisher    = {{ACM}},
  year         = {2024},
  url          = {https://doi.org/10.1145/3680528.3687691},
  doi          = {10.1145/3680528.3687691},
}
@inproceedings{guo2024diffusion,
  title={Diffusion Shape Prior for Wrinkle-Accurate Cloth Registration},
  author={Guo, Jingfan and Prada, Fabian and Xiang, Donglai and \textbf{Javier Romero} and Wu, Chenglei and Park, Hyun Soo and Shiratori, Takaaki and Saito, Shunsuke},
  booktitle={2024 International Conference on 3D Vision (3DV)},
  pages={790--799},
  year={2024},
  organization={IEEE}
}
@inproceedings{chen2024urhand,
  title={URhand: Universal relightable hands},
  author={Chen, Zhaoxi and Moon, Gyeongsik and Guo, Kaiwen and Cao, Chen and Pidhorskyi, Stanislav and Simon, Tomas and Joshi, Rohan and Dong, Yuan and Xu, Yichen and Pires, Bernardo and Wen, He and Evans, Lucas and Peng, Bo and Buffalini, Julia and Trimble, Autumn and McPhail, Kevyn and Schoeller, Melissa and Yu, Shoou-I and \textbf{Javier Romero} and Zollhoefer, Michael and Sheikh, Yaser and Lie, Ziwei and Saito, Shunsuke},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={119--129},
  year={2024}
}
@inproceedings{ng2024audio,
  title={From audio to photoreal embodiment: Synthesizing humans in conversations},
  author={Ng, Evonne and \textbf{Javier Romero} and Bagautdinov, Timur and Bai, Shaojie and Darrell, Trevor and Kanazawa, Angjoo and Richard, Alexander},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={1001--1010},
  year={2024}
}
@inproceedings{zielonka2023drivable,
  author       = {Wojciech Zielonka and
                  Timur M. Bagautdinov and
                  Shunsuke Saito and
                  Michael Zollh{\"{o}}fer and
                  Justus Thies and
                  \textbf{Javier Romero}},
  title        = {Drivable 3D Gaussian Avatars},
  booktitle    = {International Conference on 3D Vision, 3DV 2025, Singapore, March
                  25-28, 2025},
  pages        = {979--990},
  publisher    = {{IEEE}},
  year         = {2025},
}
@article{xiang2022dressing,
  title={Dressing avatars: Deep photorealistic appearance for physically simulated clothing},
  author={Xiang, Donglai and Bagautdinov, Timur and Stuyck, Tuur and Prada, Fabian and \textbf{Javier Romero} and Xu, Weipeng and Saito, Shunsuke and Guo, Jingfan and Smith, Breannan and Shiratori, Takaaki and others},
  journal={ACM Transactions on Graphics (TOG)},
  volume={41},
  number={6},
  pages={1--15},
  year={2022},
  publisher={ACM New York, NY, USA}
}
@inproceedings{bai2022autoavatar,
  title={AutoAvatar: Autoregressive neural fields for dynamic avatar modeling},
  author={Bai, Ziqian and Bagautdinov, Timur and \textbf{Javier Romero} and Zollh{\"o}fer, Michael and Tan, Ping and Saito, Shunsuke},
  booktitle={European Conference on Computer Vision},
  pages={222--239},
  year={2022},
  organization={Springer}
}
@inproceedings{ruiz2022human,
  title={Human body measurement estimation with adversarial augmentation},
  author={Ruiz, Nataniel and Bellver, Miriam and Bolkart, Timo and Arora, Ambuj and Lin, Ming C and \textbf{Javier Romero} and Bala, Raja},
  booktitle={2022 International Conference on 3D Vision (3DV)},
  pages={219--230},
  year={2022},
  organization={IEEE}
}
@inproceedings{sanyal2021learning,
  title={Learning realistic human reposing using cyclic self-supervision with 3d shape, pose, and appearance consistency},
  author={Sanyal, Soubhik and Vorobiov, Alex and Bolkart, Timo and Loper, Matthew and Mohler, Betty and Davis, Larry S and \textbf{Javier Romero} and Black, Michael J},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages={11138--11147},
  year={2021}
}
@article{Ranjan:IJCV:2020,
  title = {Learning Multi-Human Optical Flow},
  author = {Ranjan, Anurag and Hoffmann, David T and Tzionas, Dimitrios and Tang, Siyu and \textbf{Javier Romero} and Black, Michael J},
  journal = {International Journal of Computer Vision (IJCV)},
  number = {128},
  pages = {873--890},
  month = apr,
  year = {2020},
  url = {http://humanflow.is.tue.mpg.de },
  month_numeric = {4}
}

@inproceedings{SMPLpix:WACV:2020,
  title = {{SMPLpix}: Neural Avatars from {3D} Human Models},
  author = {Prokudin, Sergey and Black, Michael J. and \textbf{Javier Romero}},
  booktitle = {Winter Conference on Applications of Computer Vision (WACV)},
  pages = {1810--1819},
  month = jan,
  year = {2021},
  month_numeric = {1}
}

@inproceedings{SMPLpix:WACV:2020,
  title = {{SMPLpix}: Neural Avatars from {3D} Human Models},
  author = {Prokudin, Sergey and Black, Michael J. and \textbf{Javier Romero}},
  booktitle = {Winter Conference on Applications of Computer Vision (WACV)},
  pages = {1810--1819},
  month = jan,
  year = {2021},
  month_numeric = {1}
}

@InProceedings{Smith_2019_ICCV,
author = {Smith, David and Loper, Matthew and Hu, Xiaochen and Mavroidis, Paris and \textbf{Javier Romero}},
title = {FACSIMILE: Fast and Accurate Scans From an Image in Less Than a Second},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}
}

@article{Foster:NeuroImage:2019,
  title = {Decoding subcategories of human bodies from both body- and face-responsive cortical regions},
  author = {Foster, Celia and Zhao, Mintao and \textbf{Javier Romero} and Black, Michael J. and Mohler, Betty J. and Bartels, Andreas and B{\"u}lthoff, Isabelle},
  journal = {NeuroImage},
  volume = {202},
  number = {15},
  pages = {116085},
  month = nov,
  year = {2019},
  month_numeric = {11}
}

@conference{Prokudin_2019_ICCV,
  title = {Efficient Learning on Point Clouds With Basis Point Sets},
  author = {Prokudin, Sergey and Lassner, Christoph and \textbf{Javier Romero}},
  booktitle = {International Conference on Computer Vision},
  pages = {4332--4341},
  month = oct,
  year = {2019},
  month_numeric = {10}
}

@inproceedings{Ranjan:BMVC:2018,
  title = {Learning Human Optical Flow},
  author = {Ranjan, Anurag and \textbf{Javier Romero} and Black, Michael J.},
  booktitle = { 29th British Machine Vision Conference},
  month = sep,
  year = {2018},
  url = {https://github.com/anuragranj/humanflow},
  month_numeric = {9}
}

@inproceedings{Hesse:MICCAI:2018,
  title = {Learning an Infant Body Model from {RGB-D} Data for Accurate Full Body Motion Analysis},
  author = {Hesse, Nikolas and Pujades, Sergi and \textbf{Javier Romero} and Black, Michael J. and Bodensteiner, Christoph and Arens, Michael and Hofmann, Ulrich G. and Tacke, Uta and Hadders-Algra, Mijna and Weinberger, Raphael and Muller-Felber, Wolfgang and Schroeder, A. Sebastian},
  booktitle = {Int. Conf. on Medical Image Computing and Computer Assisted Intervention (MICCAI)},
  month = sep,
  year = {2018},
  month_numeric = {9}
}

@article{Thaler:Frontiers:2018,
  title = {Visual Perception and Evaluation of Photo-Realistic Self-Avatars From {3D} Body Scans in Males and Females},
  author = {Thaler, Anne and Piryankova, Ivelina and Stefanucci, Jeanine K. and Pujades, Sergi and de la Rosa, Stephan and Streuber, Stephan and \textbf{Javier Romero} and Black, Michael J. and Mohler, Betty J.},
  journal = {Frontiers in ICT},
  volume = {5},
  pages = {1--14},
  month = sep,
  year = {2018},
  month_numeric = {9}
}

@article{AlBorno:SCA:2018,
  title = {Robust Physics-based Motion Retargeting with Realistic Body Shapes},
  author = {Borno, Mazen Al and Righetti, Ludovic and Black, Michael J. and Delp, Scott L. and Fiume, Eugene and \textbf{Javier Romero}},
  journal = {Computer Graphics Forum},
  volume = {37},
  pages = {6:1--12},
  month = jul,
  year = {2018},
  month_numeric = {7}
}

@article{Molbert:PM:2017,
  title = {Assessing body image in anorexia nervosa using biometric self-avatars in virtual reality: Attitudinal components rather than visual body size estimation are distorted},
  author = {M{\"o}lbert, Simone Claire and Thaler, Anne and Mohler, Betty J. and Streuber, Stephan and \textbf{Javier Romero} and Black, Michael J. and Zipfel, Stephan and Karnath, Hans-Otto and Giel, Katrin Elisabeth},
  journal = {Psychological Medicine},
  volume = {48},
  number = {4},
  pages = {642--653},
  month = mar,
  year = {2018},
  month_numeric = {3}
}

@article{Thaler:PLOS:2018,
  title = {Body size estimation of self and others in females varying in {BMI}},
  author = {Thaler, Anne and Geuss, Michael N. and M\"{o}lbert, Simone C. and Giel, Katrin E. and Streuber, Stephan and \textbf{Javier Romero} and Black, Michael J. and Mohler, Betty J.},
  journal = {PLoS ONE},
  volume = {13},
  number = {2},
  month = feb,
  year = {2018},
  month_numeric = {2}
}

@article{FLAME:2017,
  title = {Learning a model of facial shape and expression from {4D} scans},
  author = {Li, Tianye and Bolkart, Timo and Black, Michael J. and Li, Hao and \textbf{Javier Romero}},
  journal = {ACM Transactions on Graphics},
  volume = {36},
  number = {6},
  pages = {194:1--194:17},
  month = nov,
  year = {2017},
  note = {Two first authors contributed equally},
  month_numeric = {11}
}

@article{MANO:SIGGRAPHASIA:2017,
  title = {Embodied Hands: Modeling and Capturing Hands and Bodies Together},
  author = {\textbf{Javier Romero} and Tzionas, Dimitrios and Black, Michael J.},
  journal = {ACM Transactions on Graphics, (Proc. SIGGRAPH Asia)},
  volume = {36},
  number = {6},
  pages = {245:1--245:17},
  series = {245:1--245:17},
  publisher = {ACM},
  month = nov,
  year = {2017},
  url = {http://doi.acm.org/10.1145/3130800.3130883},
  month_numeric = {11}
}

@inproceedings{JMartinez:ICCV:2017,
  title = {A simple yet effective baseline for 3d human pose estimation},
  author = {Martinez, Julieta and Hossain, Rayat and \textbf{Javier Romero} and Little, James J.},
  booktitle = {Proceedings IEEE International Conference on Computer Vision (ICCV)},
  publisher = {IEEE},
  address = {Piscataway, NJ, USA},
  month = oct,
  year = {2017},
  month_numeric = {10}
}

@inproceedings{balles2017coupling,
  title = {Coupling Adaptive Batch Sizes with Learning Rates},
  author = {Balles, Lukas and \textbf{Javier Romero} and Hennig, Philipp},
  booktitle = {Proceedings Conference on Uncertainty in Artificial Intelligence (UAI) 2017},
  pages = {410--419},
  editors = {Gal Elidan and Kristian Kersting},
  publisher = {Association for Uncertainty in Artificial Intelligence (AUAI)},
  month = aug,
  year = {2017},
  url = {http://auai.org/uai2017/proceedings/papers/141.pdf},
  month_numeric = {8}
}

@inproceedings{dfaust:CVPR:2017,
  title = {Dynamic {FAUST}: Registering Human Bodies in Motion},
  author = {Bogo, Federica and \textbf{Javier Romero} and Pons-Moll, Gerard and Black, Michael J.},
  booktitle = {Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017},
  publisher = {IEEE},
  address = {Piscataway, NJ, USA},
  month = jul,
  year = {2017},
  month_numeric = {7}
}

@inproceedings{Varol:CVPR:2017,
  title = {Learning from Synthetic Humans},
  author = {Varol, G{\"u}l and \textbf{Javier Romero} and Martin, Xavier and Mahmood, Naureen and Black, Michael J. and Laptev, Ivan and Schmid, Cordelia},
  booktitle = {Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017},
  publisher = {IEEE},
  address = {Piscataway, NJ, USA},
  month = jul,
  year = {2017},
  month_numeric = {7}
}

@inproceedings{Martinez:CVPR:2017,
  title = {On human motion prediction using recurrent neural networks},
  author = {Martinez, Julieta and Black, Michael J. and \textbf{Javier Romero}},
  booktitle = {Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017},
  publisher = {IEEE},
  address = {Piscataway, NJ, USA},
  month = jul,
  year = {2017},
  month_numeric = {7}
}

@inproceedings{Lassner:UP:2017,
  title = {Unite the People: Closing the Loop Between 3D and 2D Human Representations},
  author = {Lassner, Christoph and \textbf{Javier Romero} and Kiefel, Martin and Bogo, Federica and Black, Michael J. and Gehler, Peter V.},
  booktitle = {Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017},
  publisher = {IEEE},
  address = {Piscataway, NJ, USA},
  month = jul,
  year = {2017},
  month_numeric = {7}
}

@inbook{Fleming:Avatar:2017,
  title = {Appealing Avatars from {3D} Body Scans: Perceptual Effects of Stylization},
  author = {Fleming, Reuben and Mohler, Betty J. and \textbf{Javier Romero} and Black, Michael J. and Breidt, Martin},
  booktitle = {Computer Vision, Imaging and Computer Graphics Theory and Applications: 11th International Joint Conference, VISIGRAPP 2016, Rome, Italy, February 27 -- 29, 2016, Revised Selected Papers},
  pages = {175--196},
  publisher = {Springer International Publishing},
  year = {2017}
}

@inproceedings{MuVS:3DV:2017,
  title = {Towards Accurate Marker-less Human Shape and Pose Estimation over Time},
  author = {Huang, Yinghao and Bogo, Federica and Lassner, Christoph and Kanazawa, Angjoo and Gehler, Peter V. and \textbf{Javier Romero} and Akhter, Ijaz and Black, Michael J.},
  booktitle = {International Conference on 3D Vision (3DV)},
  pages = {421--430},
  year = {2017}
}

@inproceedings{Bogo:ECCV:2016,
  title = {Keep it {SMPL}: Automatic Estimation of {3D} Human Pose and Shape from a Single Image},
  author = {Bogo, Federica and Kanazawa, Angjoo and Lassner, Christoph and Gehler, Peter and \textbf{Javier Romero} and Black, Michael J.},
  booktitle = {Computer Vision -- ECCV 2016},
  pages = {561--578},
  series = {Lecture Notes in Computer Science},
  publisher = {Springer International Publishing},
  month = oct,
  year = {2016},
  month_numeric = {10}
}

@inproceedings{Fleming:GRAPP:2016,
  title = {Appealing female avatars from {3D} body scans: Perceptual effects of stylization},
  author = {Fleming, Reuben and Mohler, Betty and \textbf{Javier Romero} and Black, Michael J. and Breidt, Martin},
  booktitle = {11th Int. Conf. on Computer Graphics Theory and Applications (GRAPP)},
  month = feb,
  year = {2016},
  month_numeric = {2}
}

@article{Yeo:CMBBE:2016,
  title = {Shape estimation of subcutaneous adipose tissue using an articulated statistical shape model},
  author = {Yeo, Si Y. and \textbf{Javier Romero} and Loper, Matthew and Machann, J\"urgen and Black, Michael J.},
  journal = {Computer Methods in Biomechanics and Biomedical Engineering: Imaging and Visualization},
  volume = {0},
  number = {0},
  pages = {1-8},
  year = {2016},
  eprint = {  http://dx.doi.org/10.1080/21681163.2016.1163508 },
  url = {  http://dx.doi.org/10.1080/21681163.2016.1163508 }
}

@article{romero:THMS:2016,
  title = {The GRASP Taxonomy of Human Grasp Types},
  author = {Feix, Thomas and \textbf{Javier Romero} and Schmiedmayer, Heinz-Bodo and Dollar, Aaron M. and Kragic, Danica},
  journal = {Human-Machine Systems, IEEE Transactions on},
  volume = {46},
  number = {1},
  pages = {66-77},
  year = {2016}
}

@inproceedings{Bogo:ICCV:2015,
  title = {Detailed Full-Body Reconstructions of Moving People from Monocular {RGB-D} Sequences},
  author = {Bogo, Federica and Black, Michael J. and Loper, Matthew and \textbf{Javier Romero}},
  booktitle = {International Conference on Computer Vision (ICCV)},
  pages = {2300--2308},
  month = dec,
  year = {2015},
  month_numeric = {12}
}

@article{SMPL:2015,
  title = {{SMPL}: A Skinned Multi-Person Linear Model},
  author = {Loper, Matthew and Mahmood, Naureen and \textbf{Javier Romero} and Pons-Moll, Gerard and Black, Michael J.},
  journal = {ACM Trans. Graphics (Proc. SIGGRAPH Asia)},
  volume = {34},
  number = {6},
  pages = {248:1--248:16},
  publisher = {ACM},
  address = {New York, NY},
  month = oct,
  year = {2015},
  month_numeric = {10}
}

@article{SAP:2014,
  title = {Can I recognize my body's weight? The influence of shape and texture on the perception of self},
  author = {Piryankova, Ivelina and Stefanucci, Jeanine and \textbf{Javier Romero} and de la Rosa, Stephan and Black, Michael J. and Mohler, Betty},
  journal = {ACM Transactions on Applied Perception for the Symposium on Applied Perception},
  volume = {11},
  number = {3},
  pages = {13:1--13:18},
  month = sep,
  year = {2014},
  month_numeric = {9}
}

@inproceedings{Feix:RSSws:2010,
  title = {A Comprehensive Grasp Taxonomy},
  author = {Feix, Thomas and Pawlik, Ronald and Schmiedmayer, Heinz-Bodo and \textbf{Javier Romero} and Kragic, Danica},
  booktitle = {Robotics, Science and Systems: Workshop on Understanding the Human Hand for Advancing Robotic Manipulation},
  year = {2009}
}
@article{Feix:TRO:2012,
  title = {A metric for comparing the anthropomorphic motion capability of artificial hands},
  author = {Feix, Thomas and \textbf{Javier Romero} and Ek, Carl H. and Schmiedmayer, Heinz-Bodo and Kragic, Danica},
  pages = {974--980},
  journal = {IEEE RAS Transactions on Robotics, TRO},
  year = {2012}
}
@inproceedings{bogo:miccai:2014,
  title = {Automated Detection of New or Evolving Melanocytic Lesions Using a {3D} Body Model},
  author = {Bogo, Federica and \textbf{Javier Romero} and Peserico, Enoch and Black, Michael J.},
  booktitle = {Medical Image Computing and Computer-Assisted Intervention (MICCAI)},
  publisher = {Spring International Publishing},
  series = {Lecture Notes in Computer Science},
  month = sep,
  volume = {8673},
  pages = {593--600},
  abstract = {Detection of new or rapidly evolving melanocytic lesions is crucial for early diagnosis and treatment of melanoma.We propose a fully automated pre-screening system for detecting new lesions or changes in existing ones, on the order of 2 - 3mm, over almost the entire body surface. Our solution is based on a multi-camera 3D stereo system. The system captures 3D textured scans of a subject at different times and then brings these scans into correspondence by aligning them with a learned, parametric, non-rigid 3D body model. This means that captured skin textures are in accurate alignment across scans, facilitating the detection of new or changing lesions. The integration of lesion segmentation with a deformable 3D body model is a key contribution that makes our approach robust to changes in illumination and subject pose.},
  year = {2014},
  doi = {10.1007/978-3-319-10404-1_74}
}
@article{SAP:2014,
  title = {Can I recognize my body’s weight? The influence of shape and texture on the perception of self},
  author = {Piryankova, Ivenlina and Stefanucci, Jeanine and \textbf{Javier Romero} and de la Rosa, Stephan and Black, Michael J. and Mohler, Betty},
  month = {},
  number = {3},
  volume = {11},
  pages = {13:1--13:18},
  abstract = {The goal of this research was to investigate women’s sensitivity to changes in their perceived weight by altering the body mass index (BMI) of the participants’ personalized avatars displayed on a large-screen immersive display. We created the personalized avatars with a full-body 3D scanner that records both the participants’ body geometry and texture. We altered the weight of the personalized avatars to produce changes in BMI while keeping height, arm length and inseam fixed and exploited the correlation between body geometry and anthropometric measurements encapsulated in a statistical body shape model created from thousands of body scans. In a 2x2 psychophysical experiment, we investigated the relative importance of visual cues, namely shape (own shape vs. an average female body shape with equivalent height and BMI to the participant) and texture (own photo-realistic texture or checkerboard pattern texture) on the ability to accurately perceive own current body weight (by asking them ‘Is the avatar the same weight as you?’). Our results indicate that shape (where height and BMI are fixed) had little effect on the perception of body weight. Interestingly, the participants perceived their body weight veridically when they saw their own photo-realistic texture and significantly underestimated their body weight when the avatar had a checkerboard patterned texture. The range that the participants accepted as their own current weight was approximately a 0.83 to −6.05 BMI% change tolerance range around their perceived weight. Both the shape and the texture had an effect on the reported similarity of the body parts and the whole avatar to the participant’s body. This work has implications for new measures for patients with body image disorders, as well as researchers interested in creating personalized avatars for games, training applications or virtual reality.},
  journal = {ACM Transactions on Applied Perception for the Symposium on Applied Perception},
  year = {2014},
  doi = {http://dx.doi.org/10.1145/2641568}
}
@article{Dyna:SIGGRAPH:2015,
  title = {Dyna: A Model of Dynamic Human Shape in Motion},
  author = {Pons-Moll, Gerard and \textbf{Javier Romero} and Mahmood, Naureen and Black, Michael J.},
  publisher = {ACM},
  month = aug,
  number = {4},
  volume = {34},
  pages = {120:1--120:14},
  abstract = {To look human, digital full-body avatars need to have soft tissue deformations like those of real people. We learn a model of soft-tissue deformations from examples using a high-resolution 4D capture system and a method that accurately registers a template mesh to sequences of 3D scans. Using over 40,000 scans of ten subjects, we learn how soft tissue motion causes mesh triangles to deform relative to a base 3D body model. Our Dyna model uses a low-dimensional linear subspace to approximate soft-tissue deformation and relates the subspace coefficients to the changing pose of the body. Dyna uses a second-order auto-regressive model that predicts soft-tissue deformations based on previous deformations,
  the velocity and acceleration of the body, and the angular velocities and accelerations of the limbs. Dyna also models how deformations vary with a person’s body mass index (BMI), producing different deformations for people with different shapes. Dyna realistically represents the dynamics of soft tissue for previously unseen subjects and motions. We provide tools for animators to modify the deformations and apply them to new stylized characters.},
  journal = {ACM Transactions on Graphics, (Proc. SIGGRAPH)},
  year = {2015},
  doi = {http://dl.acm.org/citation.cfm?id=2766993}
}
@inproceedings{Romero:ICRA:2008,
  title = {Dynamic time warping for binocular hand tracking and reconstruction},
  author = {\textbf{Javier Romero} and Kragic, Danica and Kyrki, Vylle and Argyros, Antonis},
  booktitle = {IEEE International Conference on Robotics and Automation,ICRA},
  month = may,
  pages = {2289 -2294},
  year = {2008}
}
@inproceedings{Zuffi:ICCV:2013,
  title = {Estimating Human Pose with Flowing Puppets},
  author = {Zuffi, Silvia and \textbf{Javier Romero} and Schmid, Cordelia and Black, Michael J},
  booktitle = {IEEE International Conference on Computer Vision (ICCV)},
  pages = {3312-3319},
  abstract = {We address the problem of upper-body human pose estimation in uncontrolled monocular video sequences, without manual initialization. Most current methods focus on isolated video frames and often fail to correctly localize arms and hands. Inferring pose over a video sequence is advantageous because poses of people in adjacent frames exhibit properties of smooth variation due to the nature of human and camera motion.  To exploit this, previous methods have used prior knowledge about distinctive actions or generic temporal priors combined with static image likelihoods to track people in motion. Here we take a different approach based on a simple observation: Information about how a person moves from frame to frame is present in the optical flow field. We develop an approach for tracking articulated motions that "links" articulated shape models of people in adjacent frames trough the dense optical flow. Key to this approach is a 2D shape model of the body that we use to compute how the body moves over time. The resulting "flowing puppets" provide a way of integrating image evidence across frames to improve pose inference. We apply our method on a challenging dataset of TV video sequences and show state-of-the-art performance.},
  year = {2013},
  doi = {10.1109/ICCV.2013.411}
}
@article{romero_tro_2013,
  title = {Extracting Postural Synergies for Robotic Grasping},
  author = {\textbf{Javier Romero} and Feix, Thomas and Ek, Carl H. and Kjellstr\"om, Hedvig and Kragic, Danica},
  month = dec,
  number = {6},
  volume = {29},
  pages = {1342-1352},
  journal = {Robotics, IEEE Transactions on},
  year = {2013}
}
@inproceedings{romero:gcpr:2015,
  title = {FlowCap: 2D Human Pose from Optical Flow},
  author = {\textbf{Javier Romero} and Loper, Matthew and Black, Michael J.},
  booktitle = {German Conference on Pattern Recognition (GCPR)},
  abstract = {We estimate 2D human pose from video using only optical flow. The key insight is that dense optical flow can provide information about 2D body pose. Like range data, flow is largely invariant to appearance but unlike depth it can be directly computed from monocular video. We demonstrate that body parts can be detected from dense flow using the same random forest approach used by the Microsoft Kinect. Unlike range data, however, when people stop moving, there is no optical flow and they effectively disappear. To address this, our FlowCap method uses a Kalman filter to propagate body part positions and ve- locities over time and a regression method to predict 2D body pose from part centers. No range sensor is required and FlowCap estimates 2D human pose from monocular video sources containing human motion. Such sources include hand-held phone cameras and archival television video. We demonstrate 2D body pose estimation in a range of scenarios and show that the method works with real-time optical flow. The results suggest that optical flow shares invariances with range data that, when complemented with tracking, make it valuable for pose estimation.},
  year = {2015}
}
@inproceedings{Do:Humanoids:2009,
  title = {Grasp Recognition and Mapping on Humanoid Robots},
  author = {Do, Martin and \textbf{Javier Romero} and Kjellstr\"om, Hedvig and Azad, Pedram and Asfour, Tamim and Kragic, Danica and Dillmann, Rudiger},
  booktitle = {IEEE-RAS International Conference on Humanoid Robots},
  pages = {465--471},
  year = {2009}
}
@inproceedings{romero2010b,
  title = {Hands in action: real-time 3{D} reconstruction of hands in interaction with objects},
  author = {\textbf{Javier Romero} and Kjellstr\"om, Hedvig and Kragic, Danica},
  booktitle = { IEEE International Conference on Robotics and Automation (ICRA)},
  pages = {458--463},
  year = {2010}
}
@inproceedings{Romero:ICAR:2009,
  title = {Modeling and Evaluation of Human-to-Robot Mapping of Grasps},
  author = {\textbf{Javier Romero} and Kjellstr\"om, Hedivg and Kragic, Danica},
  booktitle = {International Conference on Advanced Robotics (ICAR)},
  pages = {1--6},
  year = {2009}
}
@inproceedings{Romero:ICAR:2009,
  title = {Modeling and Evaluation of Human-to-Robot Mapping of Grasps},
  author = {\textbf{Javier Romero} and Kjellstr\"om, Hedvig and Kragic, Danica},
  booktitle = {International Conference on Advanced Robotics (ICAR)},
  pages = {1--6},
  year = {2009}
}
@inproceedings{romeroHUMANOIDS09,
  title = {Monocular Real-Time 3D Articulated Hand Pose Estimation},
  author = {\textbf{Javier Romero} and Kjellstr\"om, Hedvig and Kragic, Danica},
  booktitle = {IEEE-RAS International Conference on Humanoid Robots},
  pages = {87--92},
  year = {2009}
}
@article{Romero2013555,
  title = {Non-parametric hand pose estimation with object context },
  author = {\textbf{Javier Romero} and Kjellstr\"om, Hedvig and Ek, Carl H. and Kragic, Danica},
  number = {8},
  volume = {31},
  pages = {555 - 564},
  abstract = {In the spirit of recent work on contextual recognition and estimation, we present a method for estimating the pose of human hands, employing information about the shape of the object in the hand. Despite the fact that most applications of human hand tracking involve grasping and manipulation of objects, the majority of methods in the literature assume a free hand, isolated from the surrounding environment. Occlusion of the hand from grasped objects does in fact often pose a severe challenge to the estimation of hand pose. In the presented method, object occlusion is not only compensated for, it contributes to the pose estimation in a contextual fashion; this without an explicit model of object shape. Our hand tracking method is non-parametric, performing a nearest neighbor search in a large database (.. entries) of hand poses with and without grasped objects. The system that operates in real time, is robust to self occlusions, object occlusions and segmentation errors, and provides full hand pose reconstruction from monocular video. Temporal consistency in hand pose is taken into account, without explicitly tracking the hand in the high-dim pose space. Experiments show the non-parametric method to outperform other state of the art regression methods, while operating at a significantly lower computational cost than comparable model-based hand tracking methods. },
  journal = {Image and Vision Computing },
  url = {http://www.sciencedirect.com/science/article/pii/S0262885613000656},
  year = {2013}
}
@inproceedings{2014_ICRA_brhs,
  title = {Robot Arm Pose Estimation through Pixel-Wise Part Classification},
  author = {Bohg, Jeannette and \textbf{Javier Romero} and Herzog, Alexander and Schaal, Stefan},
  booktitle = {IEEE International Conference on Robotics and Automation (ICRA) 2014},
  month = jun,
  pages = {3143--3150},
  abstract = {We propose to frame the problem of marker-less robot arm pose estimation as a pixel-wise part classification problem. As input, we use a depth image in which each pixel is classified to be either from a particular robot part or the background. The classifier is a random decision forest trained on a large number of synthetically generated and labeled depth images. From all the training samples ending up at a leaf node, a set of offsets is learned that votes for relative joint positions. Pooling these votes over all foreground pixels and subsequent clustering gives us an estimate of the true joint positions. Due to the intrinsic parallelism of pixel-wise classification, this approach can run in super real-time and is more efficient than previous ICP-like methods. We quantitatively evaluate the accuracy of this approach on synthetic data. We also demonstrate that the method produces accurate joint estimates on real data despite being purely trained on synthetic data.},
  year = {2014},
  doi = {http://dx.doi.org/10.1109/ICRA.2014.6907311}
}
@inproceedings{Kjellstrom:ECCV:2008,
  title = {Simultaneous Visual Recognition of Manipulation Actions and Manipulated Objects},
  author = {Kjellstr{\"o}m, Hedvig and \textbf{Javier Romero} and Martinez, Danica and Kragic, Danica},
  booktitle = {European Conference on Computer Vision, ECCV},
  pages = {336--349},
  year = {2008}
}
@inproceedings{Romero:IROS:2010,
  title = {Spatio-Temporal Modeling of Grasping Actions},
  author = {\textbf{Javier Romero} and Feix, Thomas and Kjellstr\"om, Heinz-Bodo and Kragic, Danica},
  booktitle = { IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS},
  pages = {2103--2108},
  year = {2010}
}
@inproceedings{Gratal:IFAC:2011,
  title = {Virtual Visual Servoing for Real-Time Robot Pose Estimation},
  author = {Gratal, Xavier and \textbf{Javier Romero} and Kragic, Danica},
  booktitle = {International Federation of Automatic Control World Congress, IFAC},
  year = {2011}
}
@article{Kjellstrom:CVIU:2010,
  title = {Visual Object-Action Recognition: Inferring Object Affordances from Human Demonstration},
  author = {Kjellstr\"om, Hedvig and \textbf{Javier Romero} and Kragic, Danica},
  pages = {81--90},
  journal = {Computer Vision and Image Understanding},
  year = {2010}
}
@inproceedings{Gratal:Mechatronics:2011,
  title = {Visual Servoing on Unknown Objects},
  author = {Gratal, Xavier and \textbf{Javier Romero} and Bohg, Jeannette and Kragic, Danica},
  booktitle = {International Federation of Automatic Control, IFAC Mechatronics: The Science of Intelligent Machines},
  pages = {423--435},
  year = {2011}
}
@inproceedings{Bogo:CVPR:2014,
  title = {{FAUST}: Dataset and evaluation for {3D} mesh registration},
  author = {Bogo, Federica and \textbf{Javier Romero} and Loper, Matthew and Black, Michael J.},
  booktitle = { Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)},
  address = {Columbus, Ohio, USA},
  month = jun,
  pages = {3794	--3801},
  abstract = {New scanning technologies are increasing the importance of 3D mesh data and the need for algorithms that can reliably align it. Surface registration is important for building full 3D models from partial scans, creating statistical shape models, shape retrieval, and tracking. The problem is particularly challenging for non-rigid and articulated objects like human bodies. While the challenges of real-world data registration are not present in existing synthetic datasets, establishing ground-truth correspondences for real 3D scans is difficult. We address this with a novel mesh registration technique that combines 3D shape and appearance information to produce high-quality alignments. We define a new dataset called FAUST that contains 300 scans of 10 people in a wide range of poses together with an evaluation methodology. To achieve accurate registration, we paint the subjects with high-frequency textures
  and use an extensive validation process to ensure accurate ground truth. We find that current shape registration methods have trouble with this real-world data. The dataset and evaluation website are available for research purposes at http://faust.is.tue.mpg.de.},
  year = {2014},
  doi = {http://dx.doi.org/10.1109/CVPR.2014.491}
}