HyperAIHyperAI
2 months ago

Semantic Segmentation-Assisted Instance Feature Fusion for Multi-Level 3D Part Instance Segmentation

Sun, Chunyu ; Tong, Xin ; Liu, Yang
Semantic Segmentation-Assisted Instance Feature Fusion for Multi-Level
  3D Part Instance Segmentation
Abstract

Recognizing 3D part instances from a 3D point cloud is crucial for 3Dstructure and scene understanding. Several learning-based approaches usesemantic segmentation and instance center prediction as training tasks and failto further exploit the inherent relationship between shape semantics and partinstances. In this paper, we present a new method for 3D part instancesegmentation. Our method exploits semantic segmentation to fuse nonlocalinstance features, such as center prediction, and further enhances the fusionscheme in a multi- and cross-level way. We also propose a semantic regioncenter prediction task to train and leverage the prediction results to improvethe clustering of instance points. Our method outperforms existing methods witha large-margin improvement in the PartNet benchmark. We also demonstrate thatour feature fusion scheme can be applied to other existing methods to improvetheir performance in indoor scene instance segmentation tasks.

Semantic Segmentation-Assisted Instance Feature Fusion for Multi-Level 3D Part Instance Segmentation | Latest Papers | HyperAI