Back
Representing 3D humans with parametric body models (eg: SMPL) allows us to control the 3D appearance of a human with explicit parameters for pose, shape and even clothing (to an extent). Implicit function based representations on the other hand, typically lack such interpretable control but can produce more detailed models as compared to parametric approaches. They also are not constrained by topology and resolution. In this talk I would like to discuss how we can combine these two directions and leverage the best of both worlds to model detailed and controllable 3D humans. I will primarily discuss the following works: (1) Combining Implicit Function Learning and Parametric Models for 3D Human Reconstruction. Bharat Lal Bhatnagar, Cristian Sminchisescu, Christian Theobalt, Gerard Pons-Moll, ECCV'20. (2) LoopReg: Self-supervised Learning of Implicit Surface Correspondences, Pose and Shape for 3D Human Mesh Registration. Bharat Lal Bhatnagar, Cristian Sminchisescu, Christian Theobalt, Gerard Pons-Moll, NeurIPS'20.
Bharat Lal Bhatnagar (Max-Planck-Institut für Informatik)
Ph.D. student
Bharat Lal Bhatnagar is currently a third year PhD student at 'Real Virtual Humans' group, Max Planck Institute for Informatics (MPI-INF), Saarland with Dr. Gerard Pons-Moll. He has previously worked at Microsoft Research, India as a Research Fellow and completed his Masters research at IIIT-H, India working with Prof. C.V. Jawahar and Dr. Chetan Arora.
More information