Abstract A 3D point cloud describes the real scene precisely and intuitively. To date how to segment diversifified elements in such an informative 3D scene is rarely discussed. In this paper, we fifirst introduce a simple and flflexible 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. Specififically, we make instance segmentation benefifit 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 signifificant improvement in 3D semantic segmentation. Code has been made available at: https://github.com/WXinlong/ASIS.