AI Paper Atlas

Research map / Point clouds / Segmentation and detection

CGA-Net: Category Guided Aggregation for Point Cloud Semantic Segmentation

Tao Lu, Limin Wang, Gangshan Wu

CVPR 2021 · Point clouds › Segmentation and detection · approach: Point cloud semantic segmentation · 48 citations (OpenAlex)

Check 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 CGA feature augmentationCloserLook3D(pseudo-grid) · S3DIS Area 5mIoU(%): 65.7 -> 68.6Improved
Add CGA feature augmentationRandLA-Net · S3DIS Area 5mIoU(%): 62.5 -> 65.4Improved
Add CGA feature augmentationMeteorNet · SynthiamIoU(%): 81.80 -> 83.75Improved
Add same-category aggregation (SAM) (ablation)CGA with CloserLook3D · S3DIS Area 5mIoU(%): 64.9 -> 68.6Improved
Add different-category relation module (DRM) (ablation)CGA with CloserLook3D · S3DIS Area 5mIoU(%): 66.5 -> 68.6Improved
Add the supervised binary classification loss (ablation)CGA with CloserLook3D · S3DIS Area 5mIoU(%): 66.7 -> 68.6Improved
Use supervised binary classification instead of cosine similarity (ablation)CGA with CloserLook3D · S3DIS Area 5mIoU(%): 66.6% -> 68.6Improved
Use predicted binary labels instead of ground-truth binary labels (ablation)CGA with CloserLook3D · S3DIS Area 5mIoU(%): 70.1% -> 68.6Hurt
Replace SAM with DRM (ablation)CGA with CloserLook3D · S3DIS Area 5mIoU(%): 68.6 -> 67.2Hurt
Replace DRM with SAM (ablation)CGA with CloserLook3D · S3DIS Area 5mIoU(%): 68.6 -> 66.2Hurt
Use subtraction instead of concatenation in DRM (ablation)CGA with CloserLook3D · S3DIS Area 5mIoU(%): 67.5 -> 68.6Improved
Use subtraction instead of addition in DRM (ablation)CGA with CloserLook3D · S3DIS Area 5mIoU(%): 67.4 -> 68.6Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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