Sherwin Bahmani

I am a Computer Science PhD student at the University of Toronto, supervised by David Lindell and Andrea Tagliasacchi.

I graduated from TU Darmstadt studying Computational Engineering. At TU Darmstadt, I was a student research assistant at the Visual Inference Lab of Stefan Roth. Furthermore, I was a working student and wrote my master thesis at the Image Understanding Group of Mercedes-Benz led by Uwe Franke and Marius Cordts. Moreover, I was involved in a research project at EPFL as part of the VITA Lab of Alexandre Alahi. Afterwards, I conducted a research project at ETH Zurich working in the Computer Vision Lab of Luc Van Gool. I was an intern at Stanford Unversity as part of the Geometric Computation Group of Leonidas Guibas. I was also working with Andrea Tagliasacchi at SFU.

Email  /  CV  /  Google Scholar  /  Twitter  /  Github

profile photo
Research

I am interested in computer vision, machine learning, and computer graphics.

AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformers
Sherwin Bahmani*, Ivan Skorokhodov*, Guocheng Qian, Aliaksandr Siarohin, Willi Menapace, Andrea Tagliasacchi, David B. Lindell, Sergey Tulyakov
arXiv 2024
arXiv / Project Page

VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control
Sherwin Bahmani, Ivan Skorokhodov, Aliaksandr Siarohin, Willi Menapace, Guocheng Qian, Michael Vasilkovsky, Hsin-Ying Lee, Chaoyang Wang, Jiaxu Zou, Andrea Tagliasacchi, David B. Lindell, Sergey Tulyakov
arXiv 2024
arXiv / Project Page

TC4D: Trajectory-Conditioned Text-to-4D Generation
Sherwin Bahmani*, Xian Liu*, Wang Yifan*, Ivan Skorokhodov, Victor Rong, Ziwei Liu, Xihui Liu, Jeong Joon Park, Sergey Tulyakov, Gordon Wetzstein, Andrea Tagliasacchi, David B. Lindell
ECCV 2024
arXiv / Project Page / Code

4D-fy: Text-to-4D Generation Using Hybrid Score Distillation Sampling
Sherwin Bahmani, Ivan Skorokhodov, Victor Rong, Gordon Wetzstein, Leonidas Guibas, Peter Wonka, Sergey Tulyakov, Jeong Joon Park, Andrea Tagliasacchi, David B. Lindell
CVPR 2024
arXiv / Project Page / Code

CC3D: Layout-Conditioned Generation of Compositional 3D Scenes
Sherwin Bahmani*, Jeong Joon Park*, Despoina Paschalidou, Xingguang Yan, Gordon Wetzstein, Leonidas Guibas, Andrea Tagliasacchi
ICCV 2023
arXiv / Project Page / Code

3D-Aware Video Generation
Sherwin Bahmani, Jeong Joon Park, Despoina Paschalidou, Hao Tang, Gordon Wetzstein, Leonidas Guibas, Luc Van Gool, Radu Timofte
TMLR 2023
arXiv / Project Page / Code

Semantic Self-adaptation: Enhancing Generalization with a Single Sample
Sherwin Bahmani*, Oliver Hahn*, Eduard Zamfir*, Nikita Araslanov, Daniel Cremers, Stefan Roth
TMLR 2023
arXiv / Code

Towards Robust and Adaptive Motion Forecasting: A Causal Representation Perspective
Yuejiang Liu, Riccardo Cadei*, Jonas Schweizer*, Sherwin Bahmani, Alexandre Alahi
CVPR 2022
arXiv / Code
Academic Service

  • Reviewer: CVPR, ICCV, ECCV, SIGGRAPH, SIGGRAPH Asia, NeurIPS

  • Source code based on Jon Barron's website.