AI Paper Atlas

Research map / 3D vision / Gaussian splatting

TRiGS: Temporal Rigid-Body Motion for Scalable 4D Gaussian Splatting

Suwoong Yeom, Joonsik Nam, Seunggyu Choi, Lucas Lee, Sangmin Kim, Jaesik Park, Joonsoo Kim, Kugjin Yun, Kyeongbo Kong, Suk-Ju Kang

ECCV 2026 · 3D vision › Gaussian splatting · approach: Deformable 4D 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
use naive SE(3) rigid motion with origin anchor and independent parameters (ablation)linear baseline · SelfCap 1200 framesPSNR: 24.83 -> 23.95Hurt
use local anchors with coupled se(3) parameterization (ablation)naive SE(3) · SelfCap 1200 framesPSNR: 23.95 -> 25.52Improved
add Bezier residual on translation only (ablation)linear baseline · SelfCap 1200 framesPSNR: 24.83 -> 25.10Improved
add hierarchical Bezier residual to local SE(3) (ablation)Local SE(3) · SelfCap 1200 framesPSNR: 25.52 -> 26.05Improved
add Bezier residual and local SE(3) vs linear baseline on memory (ablation)TRiGS · SelfCap 1200 framesGaussian count: 2.10M -> 0.50MImproved
add gauge fixing of local anchor (ablation)TRiGS · SelfCap 1200 framesPSNR: 25.15 -> 26.05Improved
add rigid regularization (ablation)TRiGS · SelfCap 1200 framesPSNR: 25.48 -> 26.05Improved
add motion smoothness loss (ablation)TRiGS · SelfCap 1200 framesPSNR: 25.66 -> 26.05Improved
add motion-guided relocation (ablation)TRiGS · SelfCap 1200 framesPSNR: 25.80 -> 26.05Improved
longer sequence (600 to 1200 frames)FTGS (reproduced) · SelfCapPSNR: 26.23 -> 25.41Hurt
longer sequence (600 to 1200 frames)TRiGS · SelfCapPSNR: 26.67 -> 26.05Hurt
TRiGS vs FTGS on standard-length N3VTRiGS · N3VPSNR: 32.80 -> 33.36Improved

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