Kaihua Chen

I’m a Master’s student in Computer Vision (MSCV) at the Robotics Institute, School of Computer Science, Carnegie Mellon University, advised by Prof. Deva Ramanan. My research broadly focuses on diffusion generative models and 3D/4D vision. Previously, I was fortunate to work as a research intern at the University of Toronto during my undergraduate studies at CAU.

Email  /  CV  /  Scholar  /  Github

Research

My current research focuses on leveraging diffusion priors, which capture both photorealistic generation and underlying 3D structure, for tasks including amodal segmentation, video understanding, depth estimation, and 4D reconstruction.

We reformulate novel-view synthesis as a structured inpainting task. CogNVS is a video diffusion model for dynamic novel-view synthesis trained in a self-supervised manner using only 2D videos!

Given a modal (visible) object sequence in a video, we develop a two-stage method that generates its amodal (visible + invisible) masks and RGB content via video diffusion.

MfH converts relative depth estimation to metric depth estimation via generative painting and human mesh recovery.

We introduce TAO-Amodal, an amodal tracking dataset featuring 833 diverse categories in thousands of video sequences.

Template borrowed from Jon Barron.
Last updated: July 23, 2025