Yang Hai(海洋)

I am a full-time researcher at Insta360.

My research interest lies in Computer Vision and Deep learning. Recently, I have been working on pose estimation and neural rendering.

Email  /  Github /  Google Schloar

• 2023.11. I am going to join Insta360 as a research engineer.

• 2023.07. One paper is accepted by ICCV 2023.

• 2023.02. Two papers are accepted by CVPR 2023.

• 2022.10. We win the Best Single-Model Method and the Best Method on LM-O in the BOP Challenge 2022. [Slides]

• 2021.03-2021.09. Research intern at Sensetime, working closely with Zhaoyang Liu.

• 2021.06. Gradute from Xidian University, ranking 5%.

• Yang Hai, Guo Wang, Tan Su, Wenjie jiang, Yinlin Hu. Hierarchical Flow Diffusion for Efficient Frame Interpolation. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2025.

• Yang Hai, Rui Song, Jiaojiao Li, David Ferstl, Yinlin Hu. Pseudo Flow Consistency for Self-Supervised 6D Object Pose Estimation. International Conference on Computer Vision (ICCV), 2023. [PDF] [Code] [Poster] [Video]

• Yang Hai, Rui Song, Jiaojiao Li, Mathieu Salzmann, Yinlin Hu. Rigidity-Aware Detection for 6D Object Pose Estimation. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023. [PDF] [Code] [Poster] [Video]

• Yang Hai, Rui Song, Jiaojiao Li, Yinlin Hu. Shape-Constraint Recurrent Flow for 6D Object Pose Estimation. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023. [PDF] [Code] [Poster] [Video]