SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2108.02350 · ICCV · 2021

Hierarchical Aggregation for 3D Instance Segmentation

Jiemin Fang, Qian Zhang, Wenyu Liu, Xinggang Wang, Shaoyu Chen

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

Instance segmentation on point clouds is a fundamental task in 3D scene perception. In this work, we propose a concise clustering-based framework named HAIS, which makes full use of spatial relation of points and point sets. Considering clustering-based methods may result in oversegmentation or under-segmentation, we introduce the hierarchical aggregation to progressively generate instance proposals, i.e., point aggregation for preliminarily clustering points to sets and set aggregation for generating complete instances from sets. Once the complete 3D instances are obtained, a sub-network of intra-instance prediction is adopted for noisy points filtering and mask quality scoring. HAIS is fast (only 410ms per frame on Titan X)) and does not require non-maximum suppression. It ranks 1st on the ScanNet v2 benchmark 1 , achieving the highest 69.9% AP 50 and surpassing previous state-of-the-art (SOTA) methods by a large margin. Besides, the SOTA results on the S3DIS dataset validate the good generalization ability. Code is available at https://github.com/hustvl/HAIS.

For agents

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

get_harvested_code_for_paper("2108.02350")
get_code_for_paper("2108.02350")
have("2108.02350")

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

curl https://syntology.ai/api/ran/2108.02350.json

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

[![Syntology run record](https://syntology.ai/api/ran/2108.02350.svg)](https://syntology.ai/paper/2108.02350)

Connect an agent — have() is free.