Associatively Segmenting Instances and Semantics in Point Clouds
This addresses the challenge of segmenting diverse elements in 3D scenes for applications like robotics and autonomous driving, representing an incremental advance by combining existing tasks with novel mutual enhancement.
The paper tackles the problem of simultaneously segmenting instances and semantics in 3D point clouds by introducing a framework that allows these tasks to mutually benefit each other, resulting in state-of-the-art performance in 3D instance segmentation and significant improvement in 3D semantic segmentation.
A 3D point cloud describes the real scene precisely and intuitively.To date how to segment diversified elements in such an informative 3D scene is rarely discussed. In this paper, we first introduce a simple and flexible framework to segment instances and semantics in point clouds simultaneously. Then, we propose two approaches which make the two tasks take advantage of each other, leading to a win-win situation. Specifically, we make instance segmentation benefit from semantic segmentation through learning semantic-aware point-level instance embedding. Meanwhile, semantic features of the points belonging to the same instance are fused together to make more accurate per-point semantic predictions. Our method largely outperforms the state-of-the-art method in 3D instance segmentation along with a significant improvement in 3D semantic segmentation. Code has been made available at: https://github.com/WXinlong/ASIS.