ICM-3D: Instantiated Category Modeling for 3D Instance Segmentation
This addresses the challenge of segmenting 3D point clouds into instances for 3D vision applications, though it appears incremental as it builds on existing deep learning approaches.
The paper tackles 3D instance segmentation by reformulating it as a per-point classification problem, proposing ICM-3D which achieves competitive performance across multiple frameworks and benchmarks.
Separating 3D point clouds into individual instances is an important task for 3D vision. It is challenging due to the unknown and varying number of instances in a scene. Existing deep learning based works focus on a two-step pipeline: first learn a feature embedding and then cluster the points. Such a two-step pipeline leads to disconnected intermediate objectives. In this paper, we propose an integrated reformulation of 3D instance segmentation as a per-point classification problem. We propose ICM-3D, a single-step method to segment 3D instances via instantiated categorization. The augmented category information is automatically constructed from 3D spatial positions. We conduct extensive experiments to verify the effectiveness of ICM-3D and show that it obtains inspiring performance across multiple frameworks, backbones and benchmarks.