AI Paper Atlas

Research map / Point clouds / Segmentation and detection

Point Cloud Instance Segmentation With Semi-Supervised Bounding-Box Mining

Yongbin Liao, Hongyuan Zhu, Yanggang Zhang, Chuangguan Ye, Tao Chen, Jiayuan Fan

TPAMI 2021 · Point clouds › Segmentation and detection · approach: Point cloud semantic segmentation · 28 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
add semi-supervised SPCR bounding box proposals instead of VoteNet trained on labeled data only (ablation)VoteNet · ScanNet v2 val (10% labeled)mAP@25%: 26.3 -> 31.4Improved
add SPCR on data-efficient detection benchmark versus CSC (ablation)SPCR · ScanNet data-efficient detection (10% data)mAP@50%: 8.6 -> 18.0Improved
add SPCR at 80% data versus CSC (ablation)SPCR · ScanNet data-efficient detection (80% data)mAP@50%: 36.7 -> 36.4No clear effect
add SPIB (semantic propagation, property graph, occupancy refinement) to VoteNet at 10% labelsVoteNet · ScanNet v2 val (10% labeled)mAP@25%: 26.3 -> 38.8Improved
add semantic propagation to DetIns baseline (ablation)DetIns · ScanNet v2 valmAP@25%: 56.9 -> 57.2Improved
add property consistency graph to semantic propagation (ablation)DetIns + SP · ScanNet v2 valmAP@25%: 57.2 -> 59.1Improved
add occupancy ratio guided refinement (ablation)DetIns + SP + PC · ScanNet v2 valmAP@25%: 59.1 -> 61.4Improved
combine coordinate, color and normal property terms instead of coordinate alone (ablation)property consistency graph · ScanNet v2 valmAP@25%: 55.1 -> 57.5Improved
combine coordinate, color and normal property terms instead of coordinate alone (ablation)property consistency graph · ScanNet v2 valmAP@50%: 32.6 -> 34.1Improved
add color to coordinate property term (ablation)property consistency graph · ScanNet v2 valmAP@25%: 55.1 -> 56.1Improved
use box-level supervision with SPIB instead of DSRG baseline (ablation)DSRG · ScanNet v2 valmAP@25%: 35.1 -> 61.4Improved
use SPIB instead of BoxMask baseline (ablation)BoxMask · ScanNet v2 valmAP@25%: 58.4 -> 61.4Improved

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