AI Paper Atlas

Research map / Point clouds / Segmentation and detection

3D Semantic Segmentation in the Wild: Learning Generalized Models for Adverse-Condition Point Clouds

Aoran Xiao, Jiaxing Huang, Weihao Xuan, Ruijie Ren, Kangcheng Liu, Dayan Guan, Abdulmotaleb El Saddik, Shijian Lu, Eric P. Xing

CVPR 2023 · Point clouds › Segmentation and detection · approach: Point cloud semantic segmentation · 59 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
Use PointDR's geometry randomization and embedding aggregation instead of the source-only baselineMinkowskiNet · SemanticKITTI→SemanticSTFmIoU: 24.4 -> 28.6Improved
Use PointDR instead of the strongest listed augmentation baselineMinkowskiNet · SynLiDAR→SemanticSTFmIoU: 15.7 -> 18.5Improved
Add contrastive loss to cross-entropy training (ablation)PointDR · SemanticKITTI→SemanticSTFmIoU: 24.4 -> 27.4Improved
Add a momentum-updated class memory bank to contrastive training (ablation)PointDR-CT · SemanticKITTI→SemanticSTFmIoU: 27.4 -> 28.6Improved
Use dropout augmentation (ablation)Source-only MinkowskiNet · SemanticKITTI→SemanticSTFmIoU: 24.4 -> 25.7Improved
Use noise perturbation augmentation (ablation)Source-only MinkowskiNet · SemanticKITTI→SemanticSTFmIoU: 24.4 -> 25.9Improved
Use flipping augmentation (ablation)Source-only MinkowskiNet · SemanticKITTI→SemanticSTFmIoU: 24.4 -> 25.2Improved
Use jittering augmentation (ablation)Source-only MinkowskiNet · SemanticKITTI→SemanticSTFmIoU: 24.4 -> 26.9Improved
Combine dropout, noise perturbation, flipping, and jittering (ablation)Source-only MinkowskiNet · SemanticKITTI→SemanticSTFmIoU: 26.9 -> 26.1Hurt
Set contrastive loss weight λcl to 0.10 rather than 0.0 (ablation)PointDR · SemanticKITTI→SemanticSTFmIoU: 24.4 -> 28.6Improved
Set contrastive loss weight λcl to 1.0 rather than 0.10 (ablation)PointDR · SemanticKITTI→SemanticSTFmIoU: 28.6 -> 25.1Hurt
Set memory-bank momentum m to 0.98 rather than 0.99 (ablation)PointDR · SemanticKITTI→SemanticSTFmIoU: 28.6 -> 28.1Hurt

Earlier methods this paper compares with

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