Zhaoyang Huang
黄昭阳
Zhaoyang Huang is the CEO of Avolution AI. He obtained his Ph.D. degree at CUHK, MMLab , advised by Prof. Hongsheng Li and Prof. Xiaogang Wang. Before that, He got his master degree and bachelor degree from Zhejiang University. He had a great research experience working in the ZJU-3DV group of State Key Lab of CAD&CG, Zhejiang University, advised by Prof. Guofeng Zhang and Prof. Xiaowei Zhou.
He is interested in video correspondence learning and generation.
Experience
CEO of Avolution AI.
Ph.D in Electronic Engineering at MMLab of The Chinese University of Hong Kong.
M.Eng in Computer Science at State Key Lab of CAD & CG of Zhejiang University.
B.Eng. in Computer Science at Zhejiang University.
Research intern at NVIDIA, Hong Kong.
Research intern at Sensetime, Hangzhou.
Research intern at Siemens, Suzhou/Beijing.
Publication
BlinkVision: A Benchmark for Optical Flow, Scene Flow and Point Tracking Estimation using RGB Frames and Events
ECCV 2024
Yijin Li*, Yichen Shen*, Zhaoyang Huang*, Shuo Chen, Weikang Bian, Xiaoyu Shi, Fu-Yun Wang, Keqiang Sun, Hujun Bao, Zhaopeng Cui, Guofeng Zhang, Hongsheng Li
ETO:Efficient Transformer-based Local Feature Matching by Organizing Multiple Homography Hypotheses
ECCV 2024
Junjie Ni, Guofeng Zhang, Guanglin Li, Xinyang Liu, Yijin Li, Zhaoyang Huang, Hujun Bao
BlinkTrack: Feature Tracking over 100 FPS via Events and Images
Arxiv 2024
Yichen Shen*, Yijin Li*, Shuo Chen, Guanglin Li, Zhaoyang Huang, Hujun Bao, Zhaopeng Cui, Guofeng Zhang
A Global Depth-Range-Free Multi-View Stereo Transformer Network with Pose Embedding
NeurIPS 2024
Yitong Dong*, Yijin Li*, Zhaoyang Huang, Weikang Bian, Jingbo Liu, Hujun Bao, Zhaopeng Cui, Hongsheng Li, Guofeng Zhang
Phased Consistency Model
NeurIPS 2024
Fu-Yun Wang, Zhaoyang Huang, Alexander William Bergman, Dazhong Shen, Peng Gao, Michael Lingelbach, Keqiang Sun, Weikang Bian, Guanglu Song, Yu Liu, Hongsheng Li, Xiaogang Wang
Paper
Project Page
Code
Be-Your-Outpainter: Mastering Video Outpainting through Input-Specific Adaptation
ECCV 2024
Fu-Yun Wang, Xiaoshi Wu, Zhaoyang Huang, Xiaoyu Shi, Dazhong Shen, Guanglu Song, Yu Liu, Hongsheng Li
Paper
Project Page
Code
ZoLA: Zero-Shot Creative Long Animation Generation with Short Video Model
ECCV 2024
Oral Presentation
Fu-Yun Wang, Zhaoyang Huang, Qiang Ma, Xudong, Weibian Kang, Yijin Li, Yu Liu, Hongsheng Li
Paper
Project Page
AnimateLCM: Accelerating the Animation of Personalized Diffusion Models and Adapters with Decoupled Consistency Learning
SIGGRAPH Asia 2024 Technical Communications 2024
Fuyun Wang, Zhaoyang Huang, Xiaoyu Shi, Weikang Bian, Guanglu Song, Yu Liu, Hongsheng Li
Paper
Project Page
Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modeling
SIGGRAPH 2024
Technical Papers Video Trailer
Xiaoyu Shi*, Zhaoyang Huang*, Fu-Yun, Wang, Weikang Bian, Dasong Li, Yi Zhang, Manyuan Zhang, Kachun Cheung, Simon See,
Hongwei Qin, Jifeng Dai, Hongsheng Li
Paper
Project Page
Context-PIPs: Persistent Independent Particles Demands Spatial Context Features
NeurIPS 2023
Spotlight
Weikang Bian*, Zhaoyang Huang*, Xiaoyu Shi, Yitong Dong, Yijin Li, Hongsheng Li
Paper
Project Page
DiffInDScene: Diffusion-based High-Quality 3D Indoor Scene Generation
CVPR 2024
Xiaoliang Ju*, Zhaoyang Huang*, Yijin Li, Guofeng Zhang, Yu Qiao, Hongsheng Li
Paper
Project Page
VideoFlow: Exploiting Temporal Cues for Multi-frame Optical Flow Estimation
ICCV 2023
Ranks 1st on Sintel Optical Flow benchmark on Mar. 15th, 2023
VideoFlow reduces the optical flow error of Sintel Clean to the sub-pixel level for the first time
Xiaoyu Shi, Zhaoyang Huang*, Weikang Bian, Dasong Li, Manyuan Zhang, Kachun Cheung, Simon See, Hongwei Qin, Jifeng Dai, Hongsheng Li*
Paper
BlinkFlow: A Dataset to Push the Limits of Event-based Optical Flow Estimation
IROS 2023
The first large-scale dataset for event-based optical flow.
Yijin Li*, Zhaoyang Huang*, Shuo Chen, Xiaoyu Shi, Hongsheng Li, Hujun Bao, Zhaopeng Cui, Guofeng Zhang
Paper
PATS: Patch Area Transportation with Subdivision for Local Feature Matching
CVPR 2023
Junjie Ni, Yijin Li, Zhaoyang Huang, Hongsheng Li, Hujun Bao, Zhaopeng Cui, Guofeng Zhang
Paper
Project Page
FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation
CVPR 2023
Ranks 1st on Sintel Optical Flow benchmark on Mar. 1th, 2023
Xiaoyu Shi*, Zhaoyang Huang*, Dasong Li, Manyuan Zhang, Kachun Cheung, Simon See, Hongwei Qin, Jifeng Dai, Hongsheng Li
Paper
NeuralMarker: A Framework for Learning General Marker Correspondence
ACM Transactions on Graphics (SIGGRAPH Asia 2022)
Zhaoyang Huang*, Xiaokun Pan*, Weihong Pan, Weikang Bian, Yan Xu, Ka Chun Cheung, Guofeng Zhang, Hongsheng Li
Paper
Project Page
Code
Controllable 3D Face Synthesis with Conditional Generative Occupancy Fields
NIPS 2022
Keqiang Sun, Shangzhe Wu, Zhaoyang Huang, Ning Zhang, Quan Wang, HongSheng Li
Paper
Project Page
Code
FlowFormer: A Transformer Architecture for Optical Flow
ECCV 2022
Ranks 1st on Sintel Optical Flow benchmark on Mar. 17th, 2022
Zhaoyang Huang*, Xiaoyu Shi*, Chao Zhang, Qiang Wang, Kachun Cheung, Hongwei Qin, Jifeng Dai, Hongsheng Li
Paper
Supp
Project Page
Code
LIFE: Lighting Invariant Flow Estimation
A previous version of NeuralMarker
Zhaoyang Huang*, Xiaokun Pan*, Runsen Xu, Yan Xu, Kachun Cheung, Guofeng Zhang, Hongsheng Li
Paper
Project Page
Code
VS-Net: Voting with Segmentation for Visual Localization
CVPR 2021
Zhaoyang Huang*, Han Zhou*, Yijin Li, Bangbang Yang, Yan Xu,
Xiaowei Zhou, Hujun Bao, Guofeng Zhang, Hongsheng Li
Paper
Project Page
Code
SelfVoxeLO: Self-supervised LiDAR Odometry with Voxel-based Deep Neural Networks
CoRL 2020
Yan Xu, Zhaoyang Huang, Kwan-Yee Lin, Xinge Zhu, Jianping Shi, Hujun Bao, Guofeng Zhang, Hongsheng Li
Paper
NIID-Net: Adapting Surface Normal Knowledge for Intrinsic Image
Decomposition in Indoor Scenes
TVCG 2020
Jundan Luo*, Zhaoyang Huang*, Yijin Li, Xiaowei Zhou, Guofeng Zhang, Hujun Bao
Paper
Project Page
Code
Prior Guided Dropout for Robust Visual Localization in Dynamic Environments
ICCV 2019
Zhaoyang Huang, Yan Xu, Jianping Shi, Xiaowei Zhou, Hujun Bao, Guofeng Zhang
Paper
Code
Poster
Honors
National Scholarship
Outstanding Graduate award