AI Paper Atlas

Research map / 3D vision / Gaussian splatting

LocalDyGS: Multi-view Global Dynamic Scene Modeling via Adaptive Local Implicit Feature Decoupling

Jiahao Wu, Rui Peng, Jianbo Jiao, Jiayu Yang, Luyang Tang, Kaiqiang Xiong, Jie Liang, Jinbo Yan, Runling Liu, Ronggang Wang

ICCV 2025 · 3D vision › Gaussian splatting · approach: Monocular dynamic scene reconstruction · 15 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 static feature shared across time to decouple from dynamic residual (ablation)LocalDyGS · N3DVPSNR (mean): 29.46 -> 31.40Improved
add Temporal Gaussian deactivation (ablation)LocalDyGS · N3DVPSNR (mean): 31.19 -> 31.40Improved
add Temporal Gaussian deactivation (ablation)LocalDyGS · N3DVFPS: 89 -> 105Improved
add Temporal Gaussian deactivation (ablation)LocalDyGS · N3DVtraining time: 40 mins -> 36 minsImproved
add Adaptive Seed Growing (ablation)LocalDyGS · MeetRoom discussion scenePSNR: 31.81 -> 33.02Improved
add Adaptive Seed Growing (ablation)LocalDyGS · MeetRoom discussion scenemodel size: 68 MB -> 96 MBHurt
increase SfM initialization frames from 1 to 6 (ablation)LocalDyGS · N3DVPSNR: 31.84 -> 32.28Improved
increase SfM initialization frames from 6 to 30 (ablation)LocalDyGS · N3DVPSNR: 32.28 -> 32.30No clear effect
increase Gaussians per seed k from 10 to 20 (ablation)LocalDyGS · N3DVPSNR: 32.28 -> 31.96Hurt
decrease Gaussians per seed k from 10 to 5 (ablation)LocalDyGS · N3DVPSNR: 32.28 -> 32.15Mixed
LocalDyGS versus 4DGS and SpaceTimeGS on large-motion data (ablation)LocalDyGS · VRU basketball (GZ)PSNR: 28.32 -> 30.58Improved
LocalDyGS versus 3DGStreamLocalDyGS · MeetRoommodel size: 1230 -> 90Improved

Later papers that compared with this method

3 later accepted papers report LocalDyGS as a baseline in their results tables; 3 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 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