Scholar
Kaihua Chen
Google Scholar ID: grE9XU0AAAAJ
Robotics Institute, Carnegie Mellon University
Citations & Impact
Citations
23
H-index
3
i10-index
0
Publications
5
Co-authors
7
list available
Publications
Resume (English only)
Academic Achievements
- 1. 'Reconstruct, Inpaint, Finetune: Dynamic Novel-view Synthesis from Monocular Videos', NeurIPS 2025
- 2. 'Using Diffusion Priors for Video Amodal Segmentation', CVPR 2025
- 3. 'Metric from Human: Zero-shot Monocular Metric Depth Estimation via Test-time Adaptation', NeurIPS 2024
- 4. 'TAO-Amodal: A Benchmark for Tracking Any Object Amodally', arXiv 2024
Research Experience
- Current research focuses on leveraging diffusion priors for tasks including amodal segmentation, video understanding, depth estimation, and 4D reconstruction. Previously, worked as a research intern at the Lin Brain Lab, University of Toronto.
Education
- Master's student in Computer Vision at the Robotics Institute, School of Computer Science, Carnegie Mellon University, advised by Prof. Deva Ramanan; previously a research intern at the Lin Brain Lab, University of Toronto during undergraduate studies at China Agricultural University.
Background
- Research interests include diffusion generative models and 3D/4D vision.
Miscellany
- Template borrowed from Jon Barron. Last updated: Oct 30, 2025.
