AI Paper Atlas

Research map / Point clouds / Segmentation and detection

SQN: Weakly-Supervised Semantic Segmentation of Large-Scale 3D Point Clouds

Qingyong Hu, Bo Yang, Guangchi Fang, Yulan Guo, Aleš Leonardis, Niki Trigoni, Andrew Markham

ECCV 2022 · Point clouds › Segmentation and detection · approach: Point cloud semantic segmentation · 186 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 semantic query to RandLA-Net under 0.1% random labelsRandLA-Net · S3DIS Area-5mIoU: 52.9 -> 61.4Improved
query features at all four encoder layers instead of only the first (ablation)SQN (0.1% labels) · S3DIS Area-5mIoU: 22.89 -> 61.41Improved
query features at all four encoder layers instead of only the last (ablation)SQN (0.1% labels) · S3DIS Area-5mIoU: 46.02 -> 61.41Improved
add the 4th-layer query to layers 1-3 (ablation)SQN (0.1% labels) · S3DIS Area-5mIoU: 54.21 -> 61.41Improved
replace PointNet++ propagation layers with semantic query decoder (ablation)SQN (0.1% labels) · S3DIS Area-5mIoU: 53.4 -> 61.4Improved
replace RandLA-Net propagation layers with semantic query decoder (ablation)SQN (0.1% labels) · ScanNet valmIoU: 51.2 -> 58.4Improved
replace RandLA-Net propagation layers with semantic query decoder (ablation)SQN (0.1% labels) · Toronto3DmIoU: 71.7 -> 77.7Improved
vary number of queried neighbours from 1 to 25 (ablation)SQN · S3DIS Area-5mIoUNo clear effect
resample which 0.1% of points are labelled over 5 runs (ablation)SQN · S3DIS Area-5mIoU: 60.42 mean, 0.93 STDNo clear effect
reduce labels from 0.1% to 0.01% (ablation)SQN · S3DIS Area-5mIoU: 61.41 -> 45.30Hurt
increase labels from 0.1% to 10% (ablation)SQN · S3DIS Area-5mIoU: 61.41 -> 64.67Improved
add SQN decoder to MinkUNet at 0.1% labelsMinkUNet · SemanticKITTI valmIoU: 55.5 -> 55.8No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 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