AI Paper Atlas

Research map / Point clouds / Segmentation and detection

ISBNet: A 3D Point Cloud Instance Segmentation Network With Instance-Aware Sampling and Box-Aware Dynamic Convolution

Tuan Duc Ngo, Binh-Son Hua, Khoi Nguyen

CVPR 2023 · Point clouds › Segmentation and detection · approach: Point cloud semantic segmentation · 77 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 ISBNet instead of the strongest baselineScanNetV2 hidden test · ScanNetV2 hidden testAP: 55.9 vs. 53.2Improved
Use ISBNet instead of the strongest baselineS3DIS 6-fold cross-validation · S3DIS 6-fold cross-validationAP: 60.8 vs. 54.4Improved
Use ISBNet instead of the strongest baselineSTPLS3D validation · STPLS3D validationAP: 49.2 vs. 46.2Improved
Replace standard FPS with IA-FPS (ablation)ISBNet baseline on ScanNetV2 validation · ScanNetV2 validationAP: 47.9 -> 49.7Improved
Add Local Aggregation Layer (ablation)ISBNet baseline on ScanNetV2 validation · ScanNetV2 validationAP: 47.9 -> 50.1Improved
Replace standard dynamic convolution with box-aware dynamic convolution (ablation)ISBNet baseline on ScanNetV2 validation · ScanNetV2 validationAP: 47.9 -> 48.6Improved
Combine IA-FPS and Local Aggregation Layer (ablation)ISBNet baseline on ScanNetV2 validation · ScanNetV2 validationAP: +5.5 AP; +6.8 AP50Improved
Add box regression auxiliary supervision (ablation)ISBNet on ScanNetV2 validation · ScanNetV2 validationAP: 52.8 -> 53.4Improved
Use predicted boxes as an extra geometric cue in dynamic convolution (ablation)ISBNet on ScanNetV2 validation · ScanNetV2 validationAP: 53.4 -> 54.5Improved
Use three Point Aggregator blocks instead of two (ablation)ISBNet on ScanNetV2 validation · ScanNetV2 validationAP: 54.5 -> 54.3Hurt
Use only one dynamic convolution layer (ablation)ISBNet on ScanNetV2 validation · ScanNetV2 validationAP: 54.5 -> 45.7Hurt
Sample 512 candidates in one IA-FPS chunk (ablation)ISBNet on ScanNetV2 validation · ScanNetV2 validationAP: 54.2 -> 53.6Hurt

Later papers that compared with this method

1 later accepted paper reports ISBNet as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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