AI Paper Atlas

Research map / Point clouds / Segmentation and detection

Efficient Point Cloud Segmentation with Geometry-Aware Sparse Networks

Maosheng Ye, Rui Wan, Shuangjie Xu, Tongyi Cao, Qifeng Chen

ECCV 2022 · Point clouds › Segmentation and detection · approach: Point cloud semantic segmentation · 31 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add multi-scale sparse projection (ablation)GASN · SemanticKITTI val (ablation)mIoU: 64.0 -> 65.8Improved
add attentive scale selection (ablation)GASN · SemanticKITTI val (ablation)mIoU: 65.8 -> 67.7Improved
add deep sparse supervision (ablation)GASN · SemanticKITTI val (ablation)mIoU: 67.7 -> 69.4Improved
use attentive scale selection instead of tensor sum (ablation)GASN · SemanticKITTI val (ablation)mIoU: 67.7 -> 69.4Improved
use attentive scale selection instead of concatenation (ablation)GASN · SemanticKITTI val (ablation)mIoU: 68.7 -> 69.4Improved
use sparse instead of dense supervision (ablation)GASN · SemanticKITTI val (ablation)mIoU: 69.5 -> 69.4No clear effect
add deep sparse supervisionSPVCNN · SemanticKITTI val (ablation)mIoU: 64.7 -> 66.1Improved
add deep sparse supervisionDRINet · SemanticKITTI val (ablation)mIoU: 67.3 -> 68.1Improved
add deep sparse supervisionCylinder3D · SemanticKITTI val (ablation)mIoU: 66.5 -> 67.8Improved
add attentive scale selectionSPVCNN · SemanticKITTI val (ablation)mIoU: 64.7 -> 66.7Improved
add attentive scale selectionDRINet · SemanticKITTI val (ablation)mIoU: 67.3 -> 67.9Improved
increase blocks from 4 to 5 (ablation)GASN · SemanticKITTI val (ablation)mIoU: 69.4 -> 69.9No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy