Updates:
Some of my collaborative works in generative AI for images and videos with the team have been featured in Meta's Cannes Lion 2025 announcement.
I will be a co-chair for BMVA Digital Human Symposium on 28th May, 2025 at London, UK.
I have joined as Research Scientist at the GenAI org at Meta AI on November 2024
I have sucessfully defended my PhD Thesis on September 2024
One paper accepted at CVPR 2024
I started a Student Researcher position at Google with Thabo Beeler on December 1, 2023
I have been selected as a Top Reviewer for NeurIPS 2023.
Generative 3D Neural Avatars
Code and paper link: SCULPT: Shape-Conditioned Unpaired Learning of Pose-dependent Clothed and Textured Human Meshes
Soubhik Sanyal, Partha Ghosh, Jinlong Yang, Michael J Black, Justus Thies, Timo Bolkart
Unconditional Video Generation
Paper link: RAVEN: Rethinking Adversarial Video Generation with Efficient Tri-plane Networks
Partha Ghosh*, Soubhik Sanyal*, Cordelia Schmid , Bernhard Scholkopf (Joint first author)
Synthesizing Human Images
Soubhik Sanyal, Alex Vorobiov, Timo Bolkart, Matt Loper, Betty Mohler, Larry Davis, Javier Romero, Michael J Black
Reconstructing 3D Pose & Shape
Soubhik Sanyal, Timo Bolkart, Haiwen Feng, Michael J. Black
Deep 3D Geometry Learning
Anurag Ranjan, Timo Bolkart, Soubhik Sanyal, Michael J. Black
Face & Object Recognition
Please check my google scholar for a full and updated list of my publications