References & Citations
Computer Science > Computer Vision and Pattern Recognition
Title: Intrinsic Appearance Decomposition Using Point Cloud Representation
(Submitted on 20 Jul 2023 (this version), latest version 28 Mar 2024 (v2))
Abstract: Intrinsic decomposition is to infer the albedo and shading from the image. Since it is a heavily ill-posed problem, previous methods rely on prior assumptions from 2D images, however, the exploration of the data representation itself is limited. The point cloud is known as a rich format of scene representation, which naturally aligns the geometric information and the color information of an image. Our proposed method, Point Intrinsic Net, in short, PoInt-Net, jointly predicts the albedo, light source direction, and shading, using point cloud representation. Experiments reveal the benefits of PoInt-Net, in terms of accuracy, it outperforms 2D representation approaches on multiple metrics across datasets; in terms of efficiency, it trains on small-scale point clouds and performs stably on any-scale point clouds; in terms of robustness, it only trains on single object level dataset, and demonstrates reasonable generalization ability for unseen objects and scenes.
Submission history
From: Xiaoyan Xing [view email][v1] Thu, 20 Jul 2023 14:51:28 GMT (7254kb,D)
[v2] Thu, 28 Mar 2024 09:54:38 GMT (11728kb,D)
Link back to: arXiv, form interface, contact.