AI Paper Atlas

Research map / 3D vision / Gaussian splatting

ULF-Loc: Unbiased Landmark Feature for Robust Visual Localization with 3D Gaussian Splatting

Yingdong Gu, Shaocheng Yan, Zhenjun Zhao, Yuan Kou, Jianxin Luo, Pengcheng Shi, Jiayuan Li

CVPR 2026 · 3D vision › Gaussian splatting · approach: Compact and efficient Gaussian splatting · 1 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 Keypoint-Consensus sampling to random sampling (ablation)ULF-Loc with alpha-blending features · Cambridge Landmarks ablationinitial pose recall 15cm/5deg: 47.2 -> 60.2Improved
add Keypoint-Consensus sampling to random sampling (ablation)ULF-Loc with GWFF · Cambridge Landmarks ablationinitial pose recall 15cm/5deg: 52.6 -> 63.1Improved
add Keypoint-Consensus sampling to farthest point sampling (ablation)ULF-Loc with GWFF · Cambridge Landmarks ablationinitial pose recall 15cm/5deg: 33.5 -> 54.1Improved
add Keypoint-Consensus sampling to random sampling (ablation)ULF-Loc with GWFF · Cambridge Landmarks ablationfinal pose recall 15cm/5deg: 69.6 -> 70.9Improved
replace alpha-blending features with GWFF (ablation)ULF-Loc with random sampling · Cambridge Landmarks ablationinitial pose recall 15cm/5deg: 47.2 -> 52.6Improved
replace alpha-blending features with GWFF (ablation)ULF-Loc with random + K.C. sampling · Cambridge Landmarks ablationfinal pose recall 15cm/5deg: 68.9 -> 70.9Improved
replace alpha-blending features with GWFF (ablation)ULF-Loc with random sampling · Cambridge Landmarks ablationfinal pose recall 50cm/5deg: 89.3 -> 90.9Improved
add Local Geometric Consistency Verification (ablation)ULF-Loc · Cambridge Landmarks ablationfinal pose recall 15cm/5deg: 70.9 -> 72.0Improved
add Local Geometric Consistency Verification (ablation)ULF-Loc · Cambridge Landmarks ablationfinal pose recall 50cm/5deg: 91.7 -> 93.7Improved
add geometric weighting to GWFF (ablation)ULF-Loc with LGCV · Cambridge Landmarks ablationfinal pose recall 15cm/5deg: 70.6 -> 72.0Improved
use landmark features on sparse landmarks instead of learning features for all GaussiansULF-Loc vs STDLoc · 7Scenes Headstraining time: 50 mins -> 5 minsImproved
use sparse landmark features instead of per-Gaussian feature fieldULF-Loc vs STDLoc · 7Scenes HeadsGPU memory: 6566 MB -> 1086 MBImproved

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