AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

DBGroup: Dual-Branch Point Grouping for Weakly Supervised 3D Semantic Instance Segmentation

Xuexun Liu, Xiaoxu Xu, Qiudan Zhang, Lin Ma, Xu Wang

AAAI 2026 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation · 0 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 GAIM instead of Bidirectional Merging (ablation)DBGroup · ScanNetV2 val (pseudo-label ablation, T=1)AP: 16.3 -> 17.4Improved
add MGB to SGB with GAIM (ablation)DBGroup · ScanNetV2 val (pseudo-label ablation, T=1)AP: 16.3 -> 17.4Improved
add SGB to MGB with GAIM (ablation)DBGroup · ScanNetV2 val (pseudo-label ablation, T=1)AP: 15.5 -> 17.4Improved
select top-alpha points class-wise (ablation)DBGroup · ScanNetV2 val (SSP/IMF ablation, T=1)AP: 23.6 -> 25.0Improved
add superpoint propagation (ablation)DBGroup · ScanNetV2 val (SSP/IMF ablation, T=1)AP: 25.0 -> 26.5Improved
add Instance Mask Filter (ablation)DBGroup · ScanNetV2 val (SSP/IMF ablation, T=1)AP: 25.4 -> 26.5Improved
increase self-training iterations from 1 to 3 (ablation)DBGroup · ScanNetV2 val (self-training iterations)AP: 26.5 -> 28.6Improved
increase self-training iterations from 3 to 5 (ablation)DBGroup · ScanNetV2 val (self-training iterations)AP: 28.6 -> 28.8No clear effect
set GAIM overlap threshold 0.4 instead of 0.2 (ablation)DBGroup · ScanNetV2 val (pseudo-label ablation, T=1) thetaAP: 17.1 -> 17.4Improved
set GAIM overlap threshold 0.4 instead of 0.6 (ablation)DBGroup · ScanNetV2 val (pseudo-label ablation, T=1) thetaAP: 16.7 -> 17.4Improved
use BFS grouping instead of class-wise DBSCAN (ablation)DBGroup · ScanNetV2 val (pseudo-label ablation, T=1)AP: 17.1 -> 17.4Improved
keep top 30% instead of 10% in semantic selection (ablation)DBGroup · ScanNetV2 val (SSP alpha ablation)AP: 21.4 -> 26.5Improved

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