AI Paper Atlas

Research map / 3D vision / Gaussian splatting

ReLaGS: Relational Language Gaussian Splatting

Yaxu Xie, Abdalla Arafa, Alireza Javanmardi, Christen Millerdurai, Jia Cheng Hu, Shaoxiang Wang, Alain Pagani, Didier Stricker

CVPR 2026 · 3D vision › Gaussian splatting · approach: Sparse-view Gaussian splatting for novel views · 2 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 Maximum Weight Pruning (ablation)ReLaGS base · LERF-OVSmean mIoU: 55.88 -> 62.04Improved
add Robust Outlier-Aware Feature Aggregation (ablation)ReLaGS Base+MWP · LERF-OVSmean mIoU: 62.04 -> 64.36Improved
add Maximum Weight Pruning (ablation)ReLaGS base · 3DSSGObject Recall@5: 0.57 -> 0.65Improved
add Robust Outlier-Aware Feature Aggregation (ablation)ReLaGS Base+MWP · 3DSSGObject Recall@5: 0.65 -> 0.68Improved
add Robust Outlier-Aware Feature Aggregation (ablation)ReLaGS Base+MWP · 3DSSGPredicate Recall@3: 0.77 -> 0.79Improved
apply light pruning threshold 5e-4 (ablation)ReLaGS · LERF-OVSmIoU: 57.84 -> 64.36Improved
raise pruning threshold to 5e-1 (ablation)ReLaGS · LERF-OVSmIoU: 64.36 -> 39.18Hurt
raise tau_lang from 3 to 4 (ablation)ReLaGS · LERF-OVSmean mIoU: 64.36 -> 63.07Hurt
lower tau_lang from 3 to 1 (ablation)ReLaGS · LERF-OVSmean mIoU: 64.36 -> 60.78Hurt
add multi-hierarchy search (ablation)ReLaGS w/o MH · ScanNet++mIoU: 0.54 -> 0.56Improved
use two transformer layers instead of one in GNN (ablation)ReLaGS GNN · 3DSSGPredicate Recall@3: 0.79 -> 0.77No clear effect
initialize edge features from node pair instead of zeros (ablation)ReLaGS GNN · 3DSSGPredicate Recall@3: 0.75 -> 0.79Mixed

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