SoftGroup for 3D Instance Segmentation on Point Clouds
Authors:
Top Cited Papers
- 1 June 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2698-2707
Abstract
Existing state-of-the-art 3D instance segmentation methods perform semantic segmentation followed by grouping. The hard predictions are made when performing semantic segmentation such that each point is associated with a single class. However, the errors stemming from hard decision propagate into grouping that results in (1) low overlaps between the predicted instance with the ground truth and (2) substantial false positives. To address the aforementioned problems, this paper proposes a 3D instance segmentation method referred to as SoftGroup by performing bottom-up soft grouping followed by top-down refinement. SoftGroup allows each point to be associated with multiple classes to mitigate the problems stemming from semantic prediction errors and suppresses false positive instances by learning to categorize them as background. Experimental results on different datasets and multiple evaluation metrics demonstrate the efficacy of SoftGroup. Its performance surpasses the strongest prior method by a significant margin of $+6.2\%$ on the ScanNet v2 hidden test set and $+6.8\%$ on S3DIS Area 5 in terms of $AP_{50}$ . Soft-Group is also fast, running at 345ms per scan with a sin-gle Titan X on ScanNet v2 dataset. The source code and trained models for both datasets are available at https://github.com/thangvubk/SoftGroup.git.
Keywords
All Related Versions
This publication has 35 references indexed in Scilit:
- Mask R-CNN2017
- Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs2017
- ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes2017
- OctNet: Learning Deep 3D Representations at High Resolutions2017
- 3D Semantic Parsing of Large-Scale Indoor Spaces2016
- VoxNet: A 3D Convolutional Neural Network for real-time object recognition2015
- The wave kernel signature: A quantum mechanical approach to shape analysis2011
- Scale-invariant heat kernel signatures for non-rigid shape recognition2010
- Fast Point Feature Histograms (FPFH) for 3D registration2009
- Aligning point cloud views using persistent feature histograms2008