AI Paper Atlas

Research map / 3D vision / Gaussian splatting

TimeFormer: Capturing Temporal Relationships of Deformable 3D Gaussians for Robust Reconstruction

Dadong Jiang, Zhi Hou, Zhihui Ke, Xianghui Yang, Xiaobo Zhou, Tie Qiu

ICCV 2025 · 3D vision › Gaussian splatting · approach: Monocular dynamic scene reconstruction · 6 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 TimeFormer to 4DGS4DGS · N3DV (multi-view, mean of 6 scenes)PSNR: 31.10 -> 31.84Improved
add TimeFormer to STGSSTGS · N3DV (multi-view, mean of 6 scenes)PSNR: 31.62 -> 32.23Improved
add TimeFormer to 4DGS4DGS · HyperNeRF (monocular, mean of 6 scenes)PSNR: 27.14 -> 28.03Improved
add TimeFormer to DeformGSDeformGS · HyperNeRF (monocular, mean of 6 scenes)PSNR: 26.09 -> 27.03Improved
add TimeFormer to DeformGSDeformGS · NeRF-DS (monocular, mean of 6 scenes)PSNR: 23.59 -> 24.10Improved
add TimeFormer to DeformGS (inference without TimeFormer)DeformGS · HyperNeRF (monocular)FPS: 30.1 -> 58.9Improved
add TimeFormer to 4DGS4DGS · N3DV (multi-view)FPS: 31.7 -> 37.9Improved
add TimeFormer to STGSSTGS · N3DV (multi-view)training time: 41 min -> 78 minHurt
share weights of the two deformation fields (add sharing) (ablation)TimeFormer + DeformGS · NeRF-DS (3 scenes: press, sieve, bell) ablationPSNR: 24.81 -> 26.04Improved
use random instead of continuous timestamp sampling (ablation)TimeFormer + DeformGS · NeRF-DS (3 scenes: press, sieve, bell) ablationPSNR: 25.78 -> 26.06Improved
increase encoder layers M from 1 to 4 (ablation)TimeFormer + DeformGS · NeRF-DS (3 scenes: press, sieve, bell) ablationPSNR: 25.96 -> 26.04No clear effect
increase time batch B from 2 to 4 (random sampling) (ablation)TimeFormer + DeformGS · NeRF-DS (3 scenes: press, sieve, bell) ablationPSNR: 25.89 -> 26.06No clear effect

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