AI Paper Atlas

Research map / 3D vision / Gaussian splatting

LangRef3DGS: Natural Language-Guided 3D Referential Segmentation from Partial Observations via 3D Gaussian Splatting

Xulun Ye, Qin Zhang, Kun Zhou

CVPR 2026 · 3D vision › Gaussian splatting · approach: Sparse-view Gaussian splatting for novel views

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 Dirichlet Process novel-class discovery to the baseline (ablation)LangRef3DGS · LERF-OVS (20% views removed)mIoU: 48.2 -> 51.0Improved
add Gradient Low-Rank mechanism on top of DP (ablation)LangRef3DGS · LERF-OVS (20% views removed)mIoU: 51.0 -> 54.1Improved
add Contrastive Graph Semantic Loss on top of DP and GLR (ablation)LangRef3DGS · LERF-OVS (20% views removed)mIoU: 54.1 -> 57.3Improved
add Dirichlet Process to the baseline (ablation)LangRef3DGS · LERF-OVS (20% views removed)mAcc: 69.1 -> 72.4Improved
increase fraction of removed RGB-D frames from 10% to 40% (ablation)LangRef3DGS · LERF-OVSmIoU: 60.5 -> 50.8Hurt
remove 20% of RGB-D views (dense to partial)LangRef3DGS · LERF-MaskmIoU: 84.9 -> 79.6Hurt
LangRef3DGS versus OpenSplat3D in dense viewLangRef3DGS · LERF-OVS (dense view, mean)mIoU: 59.70 -> 60.69Improved

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