AI Paper Atlas

Research map / 3D vision / Gaussian splatting

DASH: 4D Hash Encoding with Self-Supervised Decomposition for Real-Time Dynamic Scene Rendering

Jie Chen, Zhangchi Hu, Peixi Wu, Huyue Zhu, Hebei Li, Xiaoyan Sun

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 self-supervised dynamic-static decomposition before the 4D hash encoder (ablation)DASH · Neural 3D VideoPSNR: 31.65 -> 32.22Improved
add density control for dynamic Gaussians (ablation)DASH · Neural 3D VideoPSNR: 31.92 -> 32.22Improved
add spatio-temporal smooth regularization (ablation)DASH · Neural 3D VideoPSNR: 31.51 -> 32.22Improved
add smooth regularization (ablation)DASH · Neural 3D VideoLPIPS: 0.056 -> 0.050Improved
add decomposition to Grid4D (Grid4D+dec)Grid4D · Neural 3D VideoPSNR: 31.38 -> 31.74Improved
add decomposition to Grid4D (Grid4D+dec)Grid4D · Technicolor Light FieldPSNR: 32.59 -> 33.04Improved
add decomposition to Grid4D (Grid4D+dec)Grid4D · Technicolor Light Fieldstorage (MB): 319 -> 192Improved
add decomposition to Grid4D (Grid4D+dec)Grid4D · Technicolor Light Fieldtraining time (hours): 1.2 -> 2Hurt
replace Grid4D hash decomposition with full DASHGrid4D · Technicolor Light FieldPSNR: 32.59 -> 33.94Improved
use DASH rather than 4DGaussian planes4DGaussian · Neural 3D Video (coffee martini)Gaussian count N: 123.7k -> 106.6kImproved
use DASH rather than 4DGaussian planes4DGaussian · Neural 3D Video (coffee martini)FPS: 136.9 -> 264.3Improved

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