Sato Laboratory/Sugano Laboratory, UTokyo-IIS

Our group consists of two independent research laboratories (Y. Sato Lab. and Sugano Lab.) working closely together with a focus on computer vision.

Photo by hao wang on Unsplash

News

Three papers have been accepted to ECCV 2022.

Last updated on Jul 4, 2022

Featured Publications

CompNVS: Novel View Synthesis with Scene Completion

We introduce a scalable framework for novel view synthesis (NVS) from RGB-D images with largely incomplete scene coverage. While …

Zuoyue Li, Tianxing Fang, Zhenqiang Li, Zhaopeng Cui, Yoichi Sato, Marc Pollefeys, Martin R. Oswald

CompNVS: Novel View Synthesis with Scene Completion

Compound Prototype Matching for Few-shot Action Recognition

Few-shot action recognition aims to recognize novel action classes using only a small number of labeled training samples. In this work, …

Yifei Huang, Lijin Yang, Yoichi Sato

Compound Prototype Matching for Few-shot Action Recognition

Domain Adaptive Hand Keypoint and Pixel Localization in the Wild

We aim to improve the performance of regressing hand keypoints and segmenting pixel-level hand masks under new imaging conditions …

Takehiko Ohkawa, Yu-Jhe Li, Qichen Fu, Ryosuke Furuta, Kris Kitani, Yoichi Sato

Domain Adaptive Hand Keypoint and Pixel Localization in the Wild

Surgical Skill Assessment via Video Semantic Aggregation

Automated video-based assessment of surgical skills is a promising task in assisting young surgical trainees, especially in …

Zhenqiang Li, Ling Gu, Weimin Wang, Ryosuke Nakamura, Yoichi Sato

Surgical Skill Assessment via Video Semantic Aggregation

Semantic Image Segmentation by Dynamic Discriminative Prototypes

Semantic segmentation achieves significant success through large-scale training data. Meanwhile, few-shot semantic segmentation was …

Kaipeng Zhang, Yoichi Sato

Semantic Image Segmentation by Dynamic Discriminative Prototypes

See all publications