AI Paper Atlas

Research map / 3D vision / Gaussian splatting

StreetForward: Perceiving Dynamic Street with Feedforward Causal Dynamics

Zhongrui Yu, Zhao Wang, Yida Wang, Xueyang Zhang, Yifei Zhan, Kun Zhan

ECCV 2026 · 3D vision › Gaussian splatting · approach: Monocular dynamic scene reconstruction

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 causal masked attention (ablation)StreetForward · Waymo (dynamic only)PSNR: 22.36 -> 24.30Improved
add causal masked attention (ablation)StreetForward · Waymo (full image)PSNR: 24.07 -> 27.01Improved
use variable causal horizon instead of fixed k=1 (ablation)StreetForward · Waymo (dynamic only)PSNR: 22.96 -> 24.30Improved
add local rigidity loss L_rigid (ablation)StreetForward · Waymo (dynamic only)PSNR: 22.64 -> 24.30Improved
add backward velocity (ablation)StreetForward · Waymo (dynamic only)PSNR: 23.26 -> 24.30Improved
add forward-backward consistency loss L_fb (ablation)StreetForward · Waymo (dynamic only)SSIM: 0.721 -> 0.827Improved
add opacity stabilization loss L_alpha (ablation)StreetForward · Waymo (dynamic only)PSNR: 21.02 -> 24.30Improved
add opacity stabilization loss L_alpha (ablation)StreetForward · Waymo (full image)SSIM: 0.683 -> 0.818Improved
use StreetForward versus DGGTDGGT · Waymo (dynamic only)PSNR: 20.99 -> 24.30Improved
use StreetForward versus DGGTDGGT · Waymo (full image)PSNR: 27.41 -> 27.01Hurt
use StreetForward versus DGGTDGGT · Waymo sparse-depth (full image)depth RMSE: 4.08 -> 3.14Improved
zero-shot transfer to Carla versus DGGTDGGT · Carla zero-shot (dynamic only)PSNR: 21.32 -> 22.37Improved

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