AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Details Matter for Indoor Open-vocabulary 3D Instance Segmentation

Sanghun Jung, Jingjing Zheng, Ke Zhang, Nan Qiao, Albert Y. C. Chen, Lu Xia, Chi Liu, Yuyin Sun, Xiao Zeng, Hsiang-Wei Huang, Byron Boots, Min Sun and 1 more

ICCV 2025 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary semantic segmentation · 7 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 frame-wise sIOU instead of tracklet-wise sIOU for tracking (ablation)image-based proposals · ScanNet200 val subset class-agnosticAP50: 54.3 -> 56.1Improved
add iterative merging/removal (ablation)aggregation only · ScanNet200 val subset class-agnosticAP25: 63.5 -> 68.5Improved
add overlap removal in 2D grounding (ablation)aggregation + merging/removal · ScanNet200 val subset class-agnosticAP: 31.8 -> 33.5Improved
add iterative refinement with multi-view consensus (ablation)aggregation + merging + overlap removal · ScanNet200 val subset class-agnosticAP: 33.5 -> 35.1Improved
replace CLIP with Alpha-CLIP (ablation)OV-3DIS pipeline · ScanNet200 val Top-K 2D+3DmAP: 27.5 -> 30.5Improved
add SMS-based filtering (ablation)OV-3DIS pipeline with Alpha-CLIP · ScanNet200 val Top-K 2D+3DmAP: 30.5 -> 32.7Improved
combine image-based and point-cloud-based proposalsOurs · ScanNet200 val Top-KmAP: 25.4 -> 32.7Improved
combine image-based and point-cloud-based proposalsOurs · S3DISmAR: 35.3 -> 48.2Improved
use Alpha-CLIP classification (vs OpenYOLO3D) with ScanNet200-trained proposalsOurs (3D only) · Replica Top-1mAP: 23.7 -> 22.0Hurt
iterative merging/removal on small-object datasetOurs (2D only) · ScanNet++ class-agnosticAP: 18.5 -> 18.2No clear effect
vary image visibility threshold tau_img from 0.1 (ablation)image-based proposals · ScanNet200 val subset class-agnosticAP: 35.1 -> 16.2Hurt
vary merge threshold tau_merge from 0.3 to 0.1 (ablation)image-based proposals · ScanNet200 val subset class-agnosticAP: 35.1 -> 36.1Improved

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