SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.01509 · CVPR · 2022

SoftGroup for 3D Instance Segmentation on Point Clouds

Thanh Nguyen, Chang Yoo, Tung Luu, Thang Vu, Kookhoi Kim

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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 single Titan X on ScanNet v2 dataset. The source code and trained models for both datasets are available at https: //github.com/thangvubk/SoftGroup.git.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2203.01509")
get_code_for_paper("2203.01509")
have("2203.01509")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2203.01509.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2203.01509.svg)](https://syntology.ai/paper/2203.01509)

Connect an agent — have() is free.