Hierarchical Aggregation for 3D Instance Segmentation

2021-08-05 · ICCV 2021 10 · Shaoyu Chen, Jiemin Fang, Qian Zhang, Wenyu Liu, Xinggang Wang

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 over-segmentation 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) and does not require non-maximum suppression. It ranks 1st on the ScanNet v2 benchmark, achieving the highest 69.9% AP50 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 will be available at https://github.com/hustvl/HAIS.

📄 PDF Abstract BibTeX arXiv:2108.02350

Code (1)

hustvl/HAIS 공식 구현 pytorch

Tasks

3D Instance SegmentationClusteringInstance Segmentation Segmentation Semantic Segmentation

HAMIL: Hierarchical Aggregation-Based Multi-Instance Learning for Microscopy Image Classification

2021-03-17 · Yanlun Tu, Houchao Lei, Wei Long, Yang Yang

Multi-instance learning is common for computer vision tasks, especially in biomedical image processing. Traditional methods for multi-instance learning focus on designing feature aggregation methods and multi-instance cl…

General Classification image-classification Image Classification

Hierarchy Denoising Recursive Autoencoders for 3D Scene Layout Prediction

2019-03-09 · CVPR 2019 6 · Yifei Shi, Angel Xuan Chang, Zhelun Wu, Manolis Savva 외

Indoor scenes exhibit rich hierarchical structure in 3D object layouts. Many tasks in 3D scene understanding can benefit from reasoning jointly about the hierarchical context of a scene, and the identities of objects. We…

Denoising Object object-detection Object Detection+1

Regression of Instance Boundary by Aggregated CNN and GCN

2020-08-01 · ECCV 2020 8 · Yanda Meng, Wei Meng, Dongxu Gao, Yitian Zhao 외

This paper proposes a straightforward, intuitive deep learning approach for (biomedical) image segmentation tasks. Different from the existing dense pixel classification methods, we develop a novel multilevel aggregation…

Image Segmentation regression Semantic Segmentation

Hierarchical Spatial and Channel Aggregation for Cross-domain Few-shot Segmentation

2026-06-23 · Sujun Sun, Mingwu Ren, Haofeng Zhang arxiv

Cross-domain Few-shot Segmentation (CD-FSS) aims to learn generalizable segmentation capability from abundant annotated samples in the source domain, enabling accurate segmentation of novel classes in the target domain w…

Cross-Domain Few-Shot

LaSSM: Efficient Semantic-Spatial Query Decoding via Local Aggregation and State Space Models for 3D Instance Segmentation

2026-02-11 · Lei Yao, Yi Wang, Yawen Cui, Moyun Liu 외 arxiv

Query-based 3D scene instance segmentation from point clouds has attained notable performance. However, existing methods suffer from the query initialization dilemma due to the sparse nature of point clouds and rely on c…

3D Instance Segmentation Point Clouds