AI Paper Atlas

Research map / Point clouds / Segmentation and detection

SAQN: Semantic-based Adaptive Query Network for 3D Referring Expression Segmentation

Jiale Huang, Shangfei Wang

CVPR 2026 · Point clouds › Segmentation and detection · approach: Scene completion and instance segmentation

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
replace instance-based queries with semantic-class queries (ablation)SAQN · Multi3DRefer (3D-GRES), distractorszero-target Acc@0.5: 37.1 -> 54.9Improved
replace instance-based queries with semantic-class queries (ablation)SAQN · Multi3DRefer (3D-GRES), distractorsmulti-target Acc@0.5: 51.2 -> 49.6Hurt
replace instance-based queries with semantic-class queries (ablation)SAQN · Multi3DRefer (3D-GRES), distractorsmIoU: 50.3 -> 52.1Improved
add Adaptive Query Fusion on top of semantic queries (ablation)SAQN · Multi3DRefer (3D-GRES), distractorsmulti-target Acc@0.5: 49.6 -> 51.1Improved
add Adaptive Queries Intersection Loss on top of SQ + AQF (ablation)SAQN · Multi3DRefer (3D-GRES), distractorsmIoU: 52.5 -> 53.1Improved
add AQF and AQIL to instance-based queries (without semantic queries) (ablation)SAQN · Multi3DRefer (3D-GRES), distractorszero-target Acc@0.5: 37.1 -> 36.9No clear effect
use only adaptive queries (31) with no semantic prior (ablation)SAQN · Multi3DRefer (3D-GRES), distractorsmIoU: 53.1 -> 50.4Hurt
vary adaptive query number k2 from 10 to 15 (ablation)SAQN · Multi3DRefer (3D-GRES), distractorsmIoU: 53.1 -> 51.9Hurt
vary adaptive query number k2 from 10 to 5 (ablation)SAQN · Multi3DRefer (3D-GRES), distractorsmIoU: 53.1 -> 52.7Mixed
raise loss weight lambda_a from 1 to 10 (ablation)SAQN · Multi3DRefer (3D-GRES), distractorsmIoU: 53.1 -> 49.9Hurt
lower loss weight lambda_a from 1 to 0.1 (ablation)SAQN · Multi3DRefer (3D-GRES), distractorsmIoU: 53.1 -> 52.3Hurt
semantic-class queries versus instance-based queries (IPDN), strict thresholdSAQN · ScanRefer (3D-RES) overallAcc@0.5: 54.9 -> 53.4Hurt

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