Qitao Zhao | 赵淇涛

I'm a first-year Ph.D. student (previously MSCV) at CMU Robotics Institute, where I'm fortunate to be advised by Prof. Shubham Tulsiani. Prior to CMU, I had the privilege of working with Prof. Chen Chen as an undergraduate research intern at the University of Central Florida. I completed my undergraduate studies at Shandong University in June 2023.

I spent a wonderful summer 2025 at Adobe Research, working with Hanwen Jiang.

Email / Google Scholar / GitHub / twitter

Research

I work on 3D vision (which I believe will not go away immediately) and representation learning. I'm interested in learning useful representations from visual observations — and in figuring out what we even mean by "useful".

	E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-training Qitao Zhao, Hao Tan, Qianqian Wang, Sai Bi, Kai Zhang, Kalyan Sunkavalli, Shubham Tulsiani, Hanwen Jiang IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2026 (Highlight) paper / project page / code / twitter thread
	Flow3r: Factored Flow Prediction for Scalable Visual Geometry Learning Zhongxiao Cong, Qitao Zhao, Minsik Jeon, Shubham Tulsiani IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2026 paper / project page / code / twitter thread
	DiffusionSfM: Predicting Structure and Motion via Ray Origin and Endpoint Diffusion Qitao Zhao, Amy Lin, Jeff Tan, Jason Y. Zhang, Deva Ramanan, Shubham Tulsiani IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2025 paper / project page / code / twitter thread
	Sparse-view Pose Estimation and Reconstruction via Analysis by Generative Synthesis Qitao Zhao, Shubham Tulsiani 38th Conference on Neural Information Processing Systems (NeurIPS), 2024 paper / project page / code / twitter thread
	A Single 2D Pose with Context is Worth Hundreds for 3D Human Pose Estimation Qitao Zhao, Ce Zheng, Mengyuan Liu, Chen Chen 37th Conference on Neural Information Processing Systems (NeurIPS), 2023 paper / project page / code / video
	PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation Qitao Zhao, Ce Zheng, Mengyuan Liu, Pichao Wang, Chen Chen IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023 paper / project page / code / video

Miscellaneous

I enjoy playing basketball 🏀 with friends, and my idol is Kobe Bryant. Kobe impressed me with his diligence, concentration and high standards. He influenced every aspect of my life. R.I.P.

unique visitors since Nov 2022

Template stolen from Yijia Weng (and also Jon Barron).
Last updated: Apr 12, 2026