AI Paper Atlas

Research map / 3D vision / Gaussian splatting

ParticleGS: Learning Neural Gaussian Particle Dynamics from Videos for Prior-free Physical Motion Extrapolation

Jinsheng Quan, Qiaowei Miao, Yichao Xu, Zizhuo Lin, Ying Li, Wei Yang, Zhihui Li, Yawei Luo

CVPR 2026 · 3D vision › Gaussian splatting · approach: Monocular dynamic scene reconstruction · 3 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
use Neural ODE evolver instead of MLP (ablation)ParticleGS · Dynamic Object Datasetextrapolation PSNR: 34.551 -> 36.471Improved
use Neural ODE evolver instead of MLP (ablation)ParticleGS · Dynamic Indoor Scene Datasetextrapolation PSNR: 27.455 -> 31.103Improved
add physical (Rodrigues) decoding (ablation)ParticleGS · Dynamic Object Datasetextrapolation PSNR: 35.343 -> 36.471Improved
add physical (Rodrigues) decoding (ablation)ParticleGS · Dynamic Indoor Scene Datasetextrapolation PSNR: 28.653 -> 31.103Improved
add progressive training (ablation)ParticleGS · Dynamic Object Datasetextrapolation PSNR: 35.438 -> 36.471Improved
add progressive training (ablation)ParticleGS · Dynamic Indoor Scene Datasetextrapolation LPIPS: 0.218 -> 0.133Improved
add online neighborhood regularization (ablation)ParticleGS · Dynamic Object Datasetextrapolation PSNR: 35.986 -> 36.471Improved
add online neighborhood regularization (ablation)ParticleGS · Dynamic Indoor Scene Datasetextrapolation PSNR: 30.232 -> 31.103Improved
use F=8 dynamic fields instead of F=1 (ablation)ParticleGS · Dynamic Indoor Scene Datasetextrapolation PSNR: 28.026 -> 31.103Improved
increase dynamic fields from 8 to 16 (ablation)ParticleGS · Dynamic Object Datasetextrapolation PSNR: 36.471 -> 36.552No clear effect
use factorized encoding instead of per-Gaussian encoding (ablation)ParticleGS · Dynamic Object Datasetextrapolation PSNR: 36.391 -> 36.471Improved
ParticleGS vs velocity-field FreeGaveParticleGS · Dynamic Object Datasetextrapolation PSNR: 33.632 -> 36.471Improved

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