1 code implementation • 17 May 2022 • Dinghao Yang, Bin Wang, Weijia Li, Yiqi Lin, Conghui He
Although avoiding the extensive labors of trimap annotation, existing methods still suffer from two limitations: (1) For the single image with multiple objects, it is essential to provide extra interaction information to help determining the matting target; (2) For transparent objects, the accurate regression of alpha matte from RGB image is much more difficult compared with the opaque ones.
no code implementations • 14 Oct 2020 • Dinghao Yang, Wei Gao
In this paper, we propose a point cloud classification method based on graph neural network and manifold learning.
Ranked #67 on 3D Point Cloud Classification on ModelNet40