AI Paper Atlas

Research map / Point clouds / Segmentation and detection

Dynamic Convolution for 3D Point Cloud Instance Segmentation

Tong He, Chunhua Shen, Anton van den Hengel

TPAMI 2022 · Point clouds › Segmentation and detection · approach: Point cloud semantic segmentation · 22 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
group homogeneous points before generating filters (ablation)DyCo3D baseline · ScanNetV2 valmAP: 24.8 -> 29.4Improved
add position embeddings to grouped filters (ablation)DyCo3D · ScanNetV2 valmAP: 29.4 -> 31.8Improved
add category-aware decoding (ablation)DyCo3D · ScanNetV2 valmAP: 31.8 -> 34.1Improved
add light-weight transformer on bottleneck (ablation)DyCo3D · ScanNetV2 valmAP: 34.1 -> 34.8Improved
add position embedding to per-point filters (CondInst in 3D) (ablation)baseline · ScanNetV2 valmAP: 24.8 -> 27.0Improved
restrict CondInst positives to central areas (ablation)CondInst · ScanNetV2 valmAP: 27.0 -> 28.1Improved
replace detect-then-segment MLP/CNN with dynamic filters (ablation)DyCo3D · ScanNetV2 valmAP: 16.7 -> 34.8Improved
add extra ScoreNet (ablation)DyCo3D · ScanNetV2 valmAP: 0.3% improvementNo clear effect
add self-supervised pre-training (ablation)DyCo3D Minkowski · ScanNetV2 valmAP: 38.7 -> 39.3Improved
reduce PointGroup clustering radius from 3cm to 1cm (ablation)PointGroup · ScanNetV2 valmAP: drops 23.9% (3cm to 1cm)Hurt
vary clustering radius 3cm to 30cm (ablation)DyCo3D vs PointGroup · ScanNetV2 valmAP: drops by 2.8% vs about 9%Mixed
increase mask feature dimension D' from 2 to 32 (ablation)DyCo3D · ScanNetV2 valmAP: best at D'=16Improved

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