Collaborative Propagation on Multiple Instance Graphs for 3D Instance Segmentation with Single-point Supervision
This addresses the labor-intensive labeling problem in 3D point cloud instance segmentation for scene understanding applications, offering a novel weakly supervised solution.
The paper tackles 3D instance segmentation with minimal supervision by proposing RWSeg, a method that requires only single-point labels per object, and it achieves performance comparable to fully-supervised methods and outperforms previous weakly-supervised approaches on ScanNet-v2 and S3DIS datasets.
Instance segmentation on 3D point clouds has been attracting increasing attention due to its wide applications, especially in scene understanding areas. However, most existing methods operate on fully annotated data while manually preparing ground-truth labels at point-level is very cumbersome and labor-intensive. To address this issue, we propose a novel weakly supervised method RWSeg that only requires labeling one object with one point. With these sparse weak labels, we introduce a unified framework with two branches to propagate semantic and instance information respectively to unknown regions using self-attention and a cross-graph random walk method. Specifically, we propose a Cross-graph Competing Random Walks (CRW) algorithm that encourages competition among different instance graphs to resolve ambiguities in closely placed objects, improving instance assignment accuracy. RWSeg generates high-quality instance-level pseudo labels. Experimental results on ScanNet-v2 and S3DIS datasets show that our approach achieves comparable performance with fully-supervised methods and outperforms previous weakly-supervised methods by a substantial margin.