Improved Block Merging for 3D Point Cloud Instance Segmentation
This work addresses a specific bottleneck in 3D instance segmentation for computer vision applications, offering an incremental but impactful enhancement to existing methods.
The paper tackled the problem of instance overlap limitations in block-based 3D point cloud instance segmentation by introducing a block merging algorithm that corrects wrongly labeled points through label propagation, resulting in significant and consistent accuracy improvements across all evaluation metrics.
This paper proposes a novel block merging algorithm suitable for any block-based 3D instance segmentation technique. The proposed work improves over the state-of-the-art by allowing wrongly labelled points of already processed blocks to be corrected through label propagation. By doing so, instance overlap between blocks is not anymore necessary to produce the desirable results, which is the main limitation of the current art. Our experiments show that the proposed block merging algorithm significantly and consistently improves the obtained accuracy for all evaluation metrics employed in literature, regardless of the underlying network architecture.