AI Paper Atlas

Research map / 3D vision / Gaussian splatting

DGGT: Feedforward 4D Reconstruction of Dynamic Driving Scenes using Unposed Images

Xiaoxue Chen, Ziyi Xiong, Yuantao Chen, Gen Li, Nan Wang, Hongcheng Luo, Long Chen, Haiyang Sun, Bing Wang, Guang Chen, Hongyang Li, Ya-Qin Zhang and 2 more

CVPR 2026 · 3D vision › Gaussian splatting · approach: Monocular dynamic scene reconstruction · 30 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 lifespan parameter (ablation)DGGT · Waymo NVSPSNR: 24.21 -> 27.41Improved
add single-step diffusion refinement (ablation)DGGT · Waymo NVSPSNR: 27.32 -> 27.41Improved
add single-step diffusion refinement (ablation)DGGT · Waymo NVSLPIPS: 0.108 -> 0.109No clear effect
increase input views from 4 to 16STORM · Waymo NVSPSNR: 26.05 -> 22.98Hurt
increase input views from 4 to 16DGGT · Waymo NVSPSNR: 27.41 -> 28.14Improved
predict pose as output (pose-free) instead of inputDGGT · nuScenes zero-shotPSNR: 19.75 -> 25.31Improved
train on target dataset after WaymoDGGT · nuScenesPSNR: 25.31 -> 26.63Improved
model full 3D motion trajectories with motion head instead of velocitiesDGGT · Waymo Scene FlowEPE3D: 0.276 -> 0.183Improved
use DGGT instead of STORMfeedforward reconstruction · Waymo NVSinference time: 0.18s -> 0.39sHurt

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