Tianshu Kuai

I am a CS PhD student at the University of Montreal and Mila, advised by Prof. Noam Aigerman.

I earned my MSc from the University of Toronto under the supervision of Prof. Igor Gilitschenski. Prior to that, I received my BASc in Engineering Science from the University of Toronto, majoring in Robotics.

I am interested in topics at the intersection of computer graphics/vision and machine learning. My current research focuses on developing generative modeling techniques for 3D geometry.

Email  /  CV  /  Google Scholar  /  Github  /  LinkedIn  /  X  /  Bluesky

I am actively seeking research internship opportunities in 2027. Please feel free to reach out if you have any openings.

profile photo

Research
clean-usnob Matérn Noise for Triangulation-Agnostic Flow Matching on Meshes
Tianshu Kuai, Arman Maesumi, Daniel Ritchie, Noam Aigerman
ACM Transactions on Graphics (SIGGRAPH 2026)
project page / arXiv / code / data
clean-usnob Towards Unsupervised Blind Face Restoration using Diffusion Prior
Tianshu Kuai, Sina Honari, Igor Gilitschenski, Alex Levinshtein
WACV 2025 (Oral)
project page / arXiv / code / data
clean-usnob CAMM: Building Category-Agnostic and Animatable 3D Models from Monocular Videos
Tianshu Kuai, Akash Karthikeyan, Yash Kant, Ashkan Mirzaei, Igor Gilitschenski
CVPRW 2023
project page / arXiv / code / data
clean-usnob Self-Supervised Image-to-Point Distillation via Semantically Tolerant Contrastive Loss
Anas Mahmoud, Jordan S.K. Hu, Tianshu Kuai, Ali Harakeh, Liam Paull, Steven L. Waslander
CVPR 2023
arXiv / code
clean-usnob Point Density-Aware Voxels for LiDAR 3D Object Detection
Jordan S.K. Hu, Tianshu Kuai, Steven L. Waslander
CVPR 2022
arXiv / code

Work Experience
clean-usnob Research Intern
Samsung AI Center Toronto
May 2023 - April 2024 | Toronto, ON
clean-usnob Machine Learning Intern
Qualcomm
May 2020 - May 2021 | Toronto, ON

Academic Service
  • Conference Reviewer for CVPR, ECCV, WACV, Eurographics, AAAI.

Misc
  • I am involved in maintaining a curated list of papers in NeRF Editing at awesome-nerf-editing. We welcome contributions to continue expanding and improving this collection.