AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Geometry-Aware Cross-Modal Graph Alignment for Referring Segmentation in 3D Gaussian Splatting

Yuwen Tao, Kanglei Zhou, Chang Li, Liyuan Wang

CVPR 2026 · 3D vision › Gaussian splatting · approach: Compact and efficient Gaussian splatting

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 semantic graph (relation-aware text graph) (ablation)GeoCGA baseline · Ref-LERF Ramen / KitchenmIoU: 28.3 -> 29.5 (Ramen); 20.1 -> 23.8 (Kitchen)Improved
add 3D geometry graph (ablation)GeoCGA baseline · Ref-LERF Ramen / KitchenmIoU: 28.3 -> 30.4 (Ramen); 20.1 -> 26.5 (Kitchen)Improved
combine semantic and geometry graphs (ablation)GeoCGA · Ref-LERF Ramen / KitchenmIoU: 28.3 -> 32.1 (Ramen); 20.1 -> 30.3 (Kitchen)Improved
use edge-aware message passing instead of plain semantic GNN (ablation)GeoCGA · Ref-LERF Ramen / KitchenmIoU: 31.5 -> 32.1 (Ramen); 29.1 -> 30.3 (Kitchen)Improved
use cross-view geometric consistency loss instead of pseudo-mask loss (ablation)GeoCGA · Ref-LERF Ramen / KitchenmIoU: 30.9 -> 32.1 (Ramen); 29.4 -> 30.3 (Kitchen)Improved
add explicit relation-level matching (Eq. 10) (ablation)GeoCGA · Ref-LERF Ramen / KitchenmIoU: 31.1 -> 32.1 (Ramen); 29.5 -> 30.3 (Kitchen)Improved
replace ReferSplat with GeoCGAReferSplat · Ref-LERF (avg)mIoU: 25.0 -> 30.2Improved
replace ReferSplat with GeoCGAReferSplat · LERF-OVS (avg)mIoU: 52.6 -> 55.6Improved
replace ReferSplat with GeoCGAReferSplat · 3D-OVS (avg)mIoU: 92.9 -> 93.7Improved
GeoCGA vs LangSplat on Figurines sceneGeoCGA · LERF-OVS FigurinesmIoU: 65.1 -> 63.1 (vs LangSplat)Hurt
use object-level graphs instead of dense Gaussian featuresReferSplat · model sizetrainable parameters (M): 304.18 -> 128.48Improved
use object-level graphs and lightweight GCN alignmentReferSplat · inference costFLOPs (G): 41.82 -> 25.28Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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