Hanzhe Hu
Google Scholar / GitHub / Email / Twitter / LinkedIn / CV
hanzheh [at] cs.cmu.edu, huhz [at] pku.edu.cn
                                  

I am a final-year Ph.D. candidate at the School of Computer Science at Carnegie Mellon University, advised by Prof. Shubham Tulsiani. I am part of the CMU Computer Vision Group. During my Ph.D., I have interned at Meta FAIR and Adobe Research. I obtained my Master's degree in Computer Science from the School of EECS at Peking University, where I was advised by Prof. Liwei Wang. I also worked with Dr. Han Hu at Microsoft Research Asia (MSRA) and Prof. Xiaolong Wang at UCSD.

My research interests lie in computer vision and machine learning. Currently, I am working on video world models, unified 3D models and reasoning-based visual generation.

I am looking for full-time research positions in industry. If you are interested, please feel free to contact me.

I am always open to research collaborations. Feel free to reach out.

News

Publications (Full list can be found here.)

Predictive 4D Generation with Latent State Machines
Yue Gao*, Chen Geng*, Hanzhe Hu, Fangyun Wei, Jianfeng Xiang, Jiaolong Yang,
Jiajun Wu
Neural Information Processing Systems (NeurIPS), 2026
[Paper] [Project]

Turbo3D: Ultra-fast Text-to-3D Generation
Hanzhe Hu, Tianwei Yin, Fujun Luan, Yiwei Hu, Hao Tan, Zexiang Xu, Sai Bi,
Shubham Tulsiani*, Kai Zhang*
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2025
[Paper] [Project] [Code]

MVD-Fusion: Single-view 3D via Depth-consistent Multi-view Generation
Hanzhe Hu*, Zhizhuo Zhou*, Varun Jampani, Shubham Tulsiani
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024
[Paper] [Project] [Code]

Learning Implicit Feature Alignment Function for Semantic Segmentation
Hanzhe Hu, Yinbo Chen, Jiarui Xu, Shubhankar Borse, Hong Cai, Fatih Porikli,
Xiaolong Wang
European Conference on Computer Vision (ECCV), 2022
[Paper] [Code]

Semi-Supervised Semantic Segmentation via Adaptive Equalization Learning
Hanzhe Hu, Fangyun Wei, Han Hu, Qiwei Ye, Jinshi Cui, Liwei Wang
Neural Information Processing Systems (NeurIPS), 2021 (Spotlight)
[Paper] [Code]

Region-aware Contrastive Learning for Semantic Segmentation
Hanzhe Hu, Jinshi Cui, Liwei Wang
International Conference in Computer Vision (ICCV), 2021
[Paper] [Code]

Dense Relation Distillation with Context-aware Aggregation for Few-Shot Object Detection
Hanzhe Hu, Shuai Bai, Aoxue Li, Jinshi Cui, Liwei Wang
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021
[Paper] [Code]

Context-aware Graph Convolution Network for Target Re-identification
Deyi Ji, Haoran Wang, Hanzhe Hu, Weihao Gan, Wei Wu, Junjie Yan
AAAI Conference on Aritifical Intelligence (AAAI), 2021
[Paper]

Class-wise Dynamic Graph Convolution for Semantic Segmentation
Hanzhe Hu, Deyi Ji, Weihao Gan, Shuai Bai, Wei Wu, Junjie Yan
European Conference on Computer Vision (ECCV), 2020
[Paper]

Boundary-aware Graph Convolution for Semantic Segmentation
Hanzhe Hu, Jinshi Cui, Hongbin Zha
International Conference on Pattern Recognition (ICPR), 2020
[Paper]

Adaptive Dilated Network with Self-Correction Supervision for Counting
Shuai Bai, Zhiqun He, Yu Qiao, Hanzhe Hu, Wei Wu, Junjie Yan
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020
[Paper]


Academic Services
Experience
Teaching
Honors and Awards
Thesis

Label-Efficient Learning for Object Recognition
Hanzhe Hu
Master's Thesis, Peking University, 2022