1 code implementation • 17 Jul 2023 • Hui Ying, Tianjia Shao, He Wang, Yin Yang, Kun Zhou
Quantitative and qualitative experiments demonstrate that our method outperforms the state-of-the-art methods in shape completion, detail preservation, generalization to unseen geometries, and computational cost.
1 code implementation • ICCV 2021 • Hui Ying, He Wang, Tianjia Shao, Yin Yang, Kun Zhou
Image generation has been heavily investigated in computer vision, where one core research challenge is to generate images from arbitrarily complex distributions with little supervision.
3 code implementations • 4 Dec 2019 • Hui Ying, Zhaojin Huang, Shu Liu, Tianjia Shao, Kun Zhou
The pixel-level clustering enables EmbedMask to generate high-resolution masks without missing details from repooling, and the existence of proposal embedding simplifies and strengthens the clustering procedure to achieve high speed with higher performance than segmentation-based methods.
Ranked #84 on
Instance Segmentation
on COCO test-dev