I am a Research Scientist at Stability AI, focusing on 3D/4D generation tasks. Prior to this, I was a PhD student in the Vision and Learning Lab at UC Merced, supervised by professor Ming-Hsuan Yang. During my PhD, I was honored to work with Tony Tung and Nikolaos Sarafianos at Meta, Varun Jampani and Boqing Gong at Google, Jimei Yang at Adobe, and Chen Fang at ByteDance. Before my PhD, I received my MS in Computer Science from UC San Diego and BS in Electrical Engineering from National Taiwan University (NTU).

My research interests include weakly-supervised or unsupervised learning for video and 3D computer vision. My past experience spans the fields of video temporal consistency, object detection, domain adaptation, federated learning, as well as monocular 3D reconstruction of rigid objects, articulated shapes, and human bodies.

If you are interested in research collaboration, feel free to drop me an email with your CV.

Publications

Check my Google Scholar page for more up-to-date publications.

SV4D: Dynamic 3D Content Generation with Multi-Frame and Multi-View Consistency

Yiming Xie*, Chun-Han Yao*, Vikram Voleti, Huaizu Jiang, Varun Jampani (* equal contribution)

arXiv preprint, 2024

paper / project page / video / model / code (github)

SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusion

Vikram Voleti*, Chun-Han Yao*, Mark Boss*, Adam Letts, David Pankratz, Dmitrii Tochilkin, Christian Laforte, Robin Rombach, Varun Jampani* (* core contribution)

European Conference on Computer Vision (ECCV), 2024

paper / project page / video / model / code (github)

ANIM: Accurate Neural Implicit Model for Human Reconstruction from a Single RGB-D Image

Marco Pesavento, Yuanlu Xu, Nikolaos Sarafianos, Robert Maier, Ziyan Wang, Chun-Han Yao, Marco Volino, Edmond Boyer, Adrian Hilton, Tony Tung

Computer Vision and Pattern Recognition (CVPR), 2023

paper / project page

ARTIC3D: Learning Robust Articulated 3D Shapes from Noisy Web Image Collections

Chun-Han Yao, Amit Raj, Wei-Chih Hung, Yuanzhen Li, Michael Rubinstein, Ming-Hsuan Yang, Varun Jampani

Neural Information Processing Systems (NeurIPS), 2023

paper / project page / video / code (github)

Hi-LASSIE: High-Fidelity Articulated Shape and Skeleton Discovery from Sparse Image Ensemble

Chun-Han Yao, Wei-Chih Hung, Yuanzhen Li, Michael Rubinstein, Ming-Hsuan Yang, Varun Jampani

Computer Vision and Pattern Recognition (CVPR), 2023

paper / project page / video / code (github)

LASSIE: Learning Articulated Shapes from Sparse Image Ensemble via 3D Part Discovery

Chun-Han Yao, Wei-Chih Hung, Yuanzhen Li, Michael Rubinstein, Ming-Hsuan Yang, Varun Jampani

Neural Information Processing Systems (NeurIPS), 2022

paper / project page / video / code (github)

Learning Visibility for Robust Dense Human Body Estimation

Chun-Han Yao, Jimei Yang, Duygu Ceylan, Yi Zhou, Yang Zhou Ming-Hsuan Yang

European Conference on Computer Vision (ECCV), 2022

paper / project page / code (github)

Federated Multi-Target Domain Adaptation

Chun-Han Yao, Boqing Gong, Yin Cui, Hang Qi, Yukun Zhu, Ming-Hsuan Yang

Winter Conference on Applications of Computer Vision (WACV), 2022

paper / code (soon)

Discovering 3D Parts from Image Collections

Chun-Han Yao, Wei-Chih Hung, Varun Jampani, Ming-Hsuan Yang

International Conference on Computer Vision (ICCV), 2021

paper / project page / video / code (github)

Video Object Detection via Object-level Temporal Aggregation

Chun-Han Yao, Chen Fang, Xiaohui Shen, Yangyue Wan, Ming-Hsuan Yang

European Conference on Computer Vision (ECCV), 2020

paper / code (github)

Progressive Domain Adaption for Object Detection

Han-Kai Hsu, Chun-Han Yao, Yi-Hsuan Tsai, Wei-Chih Hung, Hung-Yu Tseng, Maneesh Singh, Ming-Hsuan Yang

Winter Conference on Applications of Computer Vision (WACV), 2020

paper / code (github)

Occlusion-aware Video Temporal Consistency

Chun-Han Yao, Chia-Yang Chang, Shao-Yi Chien

ACM Multimedia (MM), 2017

paper / code (github)

Example-based Video Color Transfer

Chun-Han Yao, Chia-Yang Chang, Shao-Yi Chien

IEEE International Conference on Multimedia and Expo (ICME), 2016

paper / code (github)


see all publications