About Me
I am a PhD student at 'Real Virtual Humans' group, Max Planck Institute for Informatics (MPI-INF), Saarland with Dr. Gerard Pons-Moll. I had previously worked at Microsoft Research, India as a Research Fellow and completed my Masters research at IIIT-H, India working with Prof. C.V. Jawahar and Dr. Chetan Arora.Research Interests
My research focus is on building realistic and smart virtual humans. I've worked on modelling 3D humans and clothing, where we explored tasks like 3D reconstruction, registrations, animation, correspondence prediction etc. from images, videos and point clouds.What's next? To build the next generation of smart virtual humans, modelling the appearance of virtual humans is necessary but not sufficient. We also need to model how humans behave in their environments. To this end, I'm currently focusing on building models of human-scene interactions.
News
- Aug'22: 2 Papers (1 Best paper honourable mention) accepted at 3DV'22.
- Jul'22: Check out RVH Mesh Registration Library . You can now easily fit SMPL/ SMPLH/ SMPLD models to your scans and point clouds.
- Jun'22: 3 Papers accepted at ECCV'22.
- March'22: We will present BEHAVE, first dataset and method to capture and track human-object interactions at CVPR'22.
- Jan'22: I'll be doing an internship at Facebook Reality Labs, Sausalito.
Publications
Xiaohan Zhang,
Bharat Lal Bhatnagar,
Sebastian Starke,
Ilya A. Petrov,
Vladimir Guzov,
Helisa Dhamo,
Eduardo Pérez Pellitero,
Gerard Pons-Moll
FORCE: Dataset and Method for Intuitive Physics Guided Human-object Interaction
in Arxiv, 2024.
FORCE: Dataset and Method for Intuitive Physics Guided Human-object Interaction
in Arxiv, 2024.
Xianghui Xie,
Bharat Lal Bhatnagar,
Jan Eric Lenssen,
Gerard Pons-Moll
Template Free Reconstruction of Human-object Interaction with Procedural Interaction Generation
in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
Highlight, 11.9% of accepted papers
Template Free Reconstruction of Human-object Interaction with Procedural Interaction Generation
in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
Highlight, 11.9% of accepted papers
Keyang Zhou,
Bharat Lal Bhatnagar,
Jan Eric Lenssen,
Gerard Pons-Moll
GEARS: Local Geometry-aware Hand-object Interaction Synthesis
in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
GEARS: Local Geometry-aware Hand-object Interaction Synthesis
in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
Berna Kabadayi,
Wojciech Zielonka,
Bharat Lal Bhatnagar,
Gerard Pons-Moll,
Justus Thies
GAN-Avatar: Controllable Personalized GAN-based Human Head Avatar
in International Conference on 3D Vision (3DV), 2024.
GAN-Avatar: Controllable Personalized GAN-based Human Head Avatar
in International Conference on 3D Vision (3DV), 2024.
Yuxuan Xue,
Bharat Lal Bhatnagar,
Riccardo Marin,
Nikolaos Sarafianos,
Yuanlu Xu,
Gerard Pons-Moll,
Tony Tung
NSF: Neural Surface Fields for Human Modeling from Monocular Depth
in ICCV, 2023.
NSF: Neural Surface Fields for Human Modeling from Monocular Depth
in ICCV, 2023.
Xianghui Xie,
Bharat Lal Bhatnagar,
Gerard Pons-Moll
Visibility Aware Human-Object Interaction Tracking from Single RGB Camera
in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023.
Visibility Aware Human-Object Interaction Tracking from Single RGB Camera
in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023.
Keyang Zhou,
Bharat Lal Bhatnagar,
Bernt Schiele,
Gerard Pons-Moll
Adjoint Rigid Transform Network: Task-conditioned Alignment of 3D Shapes
in 2022 International Conference on 3D Vision (3DV), 2022.
Adjoint Rigid Transform Network: Task-conditioned Alignment of 3D Shapes
in 2022 International Conference on 3D Vision (3DV), 2022.
Yongqin Xian,
Julian Chibane,
Bharat Lal Bhatnagar,
Bernt Schiele,
Zeynep Akata,
Gerard Pons-Moll
Any-Shot GIN: Generalizing Implicit Networks for Reconstructing Novel Classes
in 2022 International Conference on 3D Vision (3DV), 2022.
Oral - Best Paper Honourable Mention
Any-Shot GIN: Generalizing Implicit Networks for Reconstructing Novel Classes
in 2022 International Conference on 3D Vision (3DV), 2022.
Oral - Best Paper Honourable Mention
Xianghui Xie,
Bharat Lal Bhatnagar,
Gerard Pons-Moll
CHORE: Contact, Human and Object REconstruction from a single RGB image
in European Conference on Computer Vision (ECCV), 2022.
CHORE: Contact, Human and Object REconstruction from a single RGB image
in European Conference on Computer Vision (ECCV), 2022.
Xiaohan Zhang,
Bharat Lal Bhatnagar,
Sebastian Starke,
Vladimir Guzov,
Gerard Pons-Moll
COUCH: Towards Controllable Human-Chair Interactions
in European Conference on Computer Vision (ECCV), 2022.
COUCH: Towards Controllable Human-Chair Interactions
in European Conference on Computer Vision (ECCV), 2022.
Keyang Zhou,
Bharat Lal Bhatnagar,
Jan Eric Lenssen,
Gerard Pons-Moll
TOCH: Spatio-Temporal Object-to-Hand Correspondence for Motion Refinement
in European Conference on Computer Vision (ECCV), 2022.
TOCH: Spatio-Temporal Object-to-Hand Correspondence for Motion Refinement
in European Conference on Computer Vision (ECCV), 2022.
Bharat Lal Bhatnagar,
Xianghui Xie,
Ilya A. Petrov,
Cristian Sminchisescu,
Christian Theobalt,
Gerard Pons-Moll
BEHAVE: Dataset and Method for Tracking Human Object Interactions
in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
BEHAVE: Dataset and Method for Tracking Human Object Interactions
in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
Bharat Lal Bhatnagar,
Cristian Sminchisescu,
Christian Theobalt,
Gerard Pons-Moll
LoopReg: Self-supervised Learning of Implicit Surface Correspondences, Pose and Shape for 3D Human Mesh Registration
in Advances in Neural Information Processing Systems (NeurIPS), 2020.
Oral
LoopReg: Self-supervised Learning of Implicit Surface Correspondences, Pose and Shape for 3D Human Mesh Registration
in Advances in Neural Information Processing Systems (NeurIPS), 2020.
Oral
Garvita Tiwari,
Bharat Lal Bhatnagar,
Tony Tung,
Gerard Pons-Moll
SIZER: A Dataset and Model for Parsing 3D Clothing and Learning Size Sensitive 3D Clothing
in European Conference on Computer Vision (ECCV), 2020.
Oral
SIZER: A Dataset and Model for Parsing 3D Clothing and Learning Size Sensitive 3D Clothing
in European Conference on Computer Vision (ECCV), 2020.
Oral
Bharat Lal Bhatnagar,
Cristian Sminchisescu,
Christian Theobalt,
Gerard Pons-Moll
Combining Implicit Function Learning and Parametric Models for 3D Human Reconstruction
in European Conference on Computer Vision (ECCV), 2020.
Oral
Combining Implicit Function Learning and Parametric Models for 3D Human Reconstruction
in European Conference on Computer Vision (ECCV), 2020.
Oral
Keyang Zhou,
Bharat Lal Bhatnagar,
Gerard Pons-Moll
Unsupervised Shape and Pose Disentanglement for 3D Meshes
in European Conference on Computer Vision (ECCV), 2020.
Unsupervised Shape and Pose Disentanglement for 3D Meshes
in European Conference on Computer Vision (ECCV), 2020.
Bharat Lal Bhatnagar,
Garvita Tiwari,
Christian Theobalt,
Gerard Pons-Moll
Multi-Garment Net: Learning to Dress 3D People from Images
in IEEE International Conference on Computer Vision (ICCV), 2019.
Multi-Garment Net: Learning to Dress 3D People from Images
in IEEE International Conference on Computer Vision (ICCV), 2019.
Thiemo Alldieck,
Marcus Magnor,
Bharat Lal Bhatnagar,
Christian Theobalt,
Gerard Pons-Moll
Learning to Reconstruct People in Clothing from a Single RGB Camera
in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
Learning to Reconstruct People in Clothing from a Single RGB Camera
in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019.