AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Rethinking Pose Refinement in 3D Gaussian Splatting under Pose Prior and Geometric Uncertainty

Mangyu Kong, Jaewon Lee, Seongwon Lee, Euntai Kim

CVPR 2026 · 3D vision › Gaussian splatting · approach: Compact and efficient Gaussian splatting · 0 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 Monte Carlo pose sampling and Fisher-information PnP to GS-CPR refinementDFNet prior · 7Scenesrecall within [2cm, 2deg]: 76.5 -> 95.1Improved
use probabilistic UGS-Loc instead of iterating the deterministic GS-CPR twice (ablation)DFNet prior · 7Scenesrecall within [2cm, 2deg]: 86.1 -> 95.1Improved
iterate deterministic GS-CPR a second time (ablation)GS-CPR with ACE prior · 7Scenesrecall within [2cm, 2deg]: 93.1 -> 93.1No clear effect
iterate deterministic GS-CPR a second time (ablation)GS-CPR with DFNet prior · 7Scenesrecall within [2cm, 2deg]: 76.5 -> 86.1Improved
add UGS-Loc to a weak pose priorDFNet · Cambridge Landmarks (avg)median translation error (cm) / rotation (deg): 26/0.51 -> 10.7/0.20Improved
increase number of particles from 2 to 16 (ablation)UGS-Loc with DFNet prior · Cambridge Landmarks (avg)median translation (cm) / rotation (deg) error: 11.8/0.24 -> 10.3/0.20Improved
increase number of particles from 2 to 16 (ablation)UGS-Loc with ACE prior · Cambridge Landmarks (avg)median translation (cm) / rotation (deg) error: 10.9/0.51 -> 9.6/0.20Improved
use MASt3R matcher instead of SuperPoint + LightGlue (ablation)UGS-Loc with DFNet prior · Cambridge Landmarks (avg)median translation (cm) / rotation (deg) error: 13/0.26 -> 11/0.20Improved
use MASt3R matcher instead of SuperPoint + LightGlue (ablation)UGS-Loc with ACE prior · Cambridge Landmarks (avg)median translation (cm) / rotation (deg) error: 11/0.26 -> 11/0.21No clear effect
swap in SuperPoint + LightGlue matcher in UGS-Loc versus GS-CPR baseline (ablation)UGS-Loc with DFNet prior · Cambridge Landmarks (avg)median translation (cm) / rotation (deg) error: 26/0.51 -> 13/0.26Improved
add UGS-Loc refinement to ACE prior on 12ScenesACE + GS-CPR · 12Scenesrecall within [2cm, 2deg]: 98.7 -> 99.1Improved
add UGS-Loc refinement to Marepo prior on 12ScenesMarepo + GS-CPR · 12Scenesrecall within [2cm, 2deg]: 90.9 -> 95.3Improved

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