SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation

Abstract

Most existing point cloud instance and semantic segmentation methods rely heavily on strong supervision signals, which require point-level labels for every point in the scene. However, such strong supervision suffers from large annotation costs, arousing the need to study efficient annotating. In this paper, we discover that the locations of instances matter for both instance and semantic 3D scene segmentation. By fully taking advantage of locations, we design a weakly-supervised point cloud segmentation method that only requires clicking on one point per instance to indicate its location for annotation. With over-segmentation for pre-processing, we extend these location annotations into segments as seg-level labels. We further design a segment grouping network (SegGroup) to generate point-level pseudo labels under seg-level labels by hierarchically grouping the unlabeled segments into the relevant nearby labeled segments, so that existing point-level supervised segmentation models can directly consume these pseudo labels for training. Experimental results show that our seg-level supervised method (SegGroup) achieves comparable results with the fully annotated point-level supervised methods. Moreover, it outperforms the recent weakly-supervised methods given a fixed annotation budget. Code is available at https://github.com/AnTao97/SegGroup.

References in corpus (9)

• Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
• Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
• MeshCNN: A Network with an Edge
• ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes
• Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds
• PRA-Net: Point Relation-Aware Network for 3D Point Cloud Analysis
• JSENet: Joint Semantic Segmentation and Edge Detection Network for 3D Point Clouds
• Learning to Exploit the Prior Network Knowledge for Weakly-Supervised Semantic Segmentation
• Weakly Supervised Semantic Point Cloud Segmentation:Towards 10X Fewer Labels

Cited by in corpus (6)

• Generative Reasoning Integrated Label Noise Robust Deep Image Representation Learning
• NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereo
• PLGS: Robust Panoptic Lifting with 3D Gaussian Splatting
• Adaptive Margin Contrastive Learning for Ambiguity-aware 3D Semantic Segmentation
• LiDAR Remote Sensing Meets Weak Supervision: Concepts, Methods, and Perspectives
• Point Cloud Instance Segmentation with Semi-supervised Bounding-Box Mining