Semantic segmentation-assisted instance feature fusion for multi-level 3D part instance segmentation

Abstract Recognizing 3D part instances from a point cloud is crucial for structure and scene understanding. Several learning-based approaches use semantic segmentation instance center prediction as training tasks fail to further exploit the inherent relationship between shape semantics instances. In this paper, we present new method segmentation. Our exploits fuse nonlocal features, such prediction, enhances fusion scheme in multi- cross-level way. We also propose region task train leverage results improve clustering of points. outperforms existing methods with large-margin improvement PartNet benchmark. demonstrate that our feature can be applied other their performance indoor tasks.