AI Paper Atlas

Research map / 3D vision / Gaussian splatting

SharpTimeGS: Sharp and Stable Dynamic Gaussian Splatting via Lifespan Modulation

Zhanfeng Liao, Jiajun Zhang, Hanzhang Tu, Zhixi Wang, Yunqi Gao, Hongwen Zhang, Yebin Liu

CVPR 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
add decoupled lifespan-based 4D representation instead of coupled 4DGS representation (ablation)SharpTimeGS · SelfCap (partial ablation)PSNR: 25.96 -> 27.36Improved
add decoupled lifespan-based 4D representation instead of coupled 4DGS representation (ablation)SharpTimeGS · SelfCap (partial ablation)LPIPS: 0.299 -> 0.244Improved
add learnable lifespan r with flat-top visibility instead of Gaussian visibility (ablation)SharpTimeGS · SelfCap (partial ablation)PSNR: 26.76 -> 27.36Improved
add learnable lifespan r with flat-top visibility instead of Gaussian visibility (ablation)SharpTimeGS · SelfCap (partial ablation)LPIPS: 0.321 -> 0.244Improved
add lifespan-velocity-aware densification instead of 4DGS densification (ablation)SharpTimeGS · SelfCap (partial ablation)PSNR: 26.82 -> 27.36Improved
add lifespan-velocity-aware densification instead of 4DGS densification (ablation)SharpTimeGS · SelfCap (partial ablation)SSIM2: 0.919 -> 0.947Improved
add velocity-aware initialization instead of zero-velocity point cloud init (ablation)SharpTimeGS · SelfCap (partial ablation)PSNR: 26.83 -> 27.36Improved
add velocity-aware initialization instead of zero-velocity point cloud init (ablation)SharpTimeGS · SelfCap (partial ablation)LPIPS: 0.297 -> 0.244Improved

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