AI Paper Atlas

Research map / 3D vision / Gaussian splatting

GAGS: Granularity-Aware Feature Distillation for Language Gaussian Splatting

Yuning Peng, Haiping Wang, Yuan Liu, Chenglu Wen, Zhen Dong, Bisheng Yang

AAAI 2026 · 3D vision › Gaussian splatting · approach: Compact and efficient Gaussian splatting · 18 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 granularity-aware distillation (GaD) (ablation)GAGS baseline · Mip-NeRF360 (4 annotated scenes)mAcc: 76.84 -> 86.27Improved
add granularity-aware distillation (GaD) (ablation)GAGS baseline · Mip-NeRF360 (4 annotated scenes)mIoU: 53.72 -> 60.99Improved
add granularity-aware segmentation (GaS) on top of GaD (ablation)GAGS · Mip-NeRF360 (4 annotated scenes)mIoU: 60.99 -> 65.09Improved
add GaS on top of GaD (ablation)GAGS · Mip-NeRF360 (4 annotated scenes)mAcc: 86.27 -> 88.67Improved
distill only subpart granularity instead of adaptive selection (ablation)GAGS · Mip-NeRF360 (4 annotated scenes)mIoU: 65.09 -> 47.78Hurt
distill only part granularity instead of adaptive selection (ablation)GAGS · Mip-NeRF360 (4 annotated scenes)mIoU: 65.09 -> 61.68Hurt
distill only whole granularity instead of adaptive selection (ablation)GAGS · Mip-NeRF360 (4 annotated scenes)mIoU: 65.09 -> 58.63Hurt
average CLIP features across the three granularities (ablation)GAGS with GaS · Mip-NeRF360 (4 annotated scenes)mIoU: 65.09 -> 59.45Hurt
use one unified feature field with adaptive granularity instead of three fieldsLangSplat · ramen (LERF)inference time (s): 49 -> 24Improved
use unified field instead of LangSplat's multiple fieldsLangSplat · LERF (4 scenes)overall mAcc: 70.49 -> 79.14Improved
use unified field instead of LangSplat's multiple fieldsLangSplat · Mip-NeRF360 (4 annotated scenes)overall mAcc: 75.48 -> 88.67Improved
self-supervised granularity selectionGAGS · complex scenes (failure cases)component-level recognitionHurt

Later papers that compared with this method

4 later accepted papers report GAGS as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.

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