AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Unraveling the Effects of Synthetic Data on End-to-End Autonomous Driving

Junhao Ge, Zuhong Liu, Longteng Fan, Yifan Jiang, Jiaqi Su, Yiming Li, Zhejun Zhang, Siheng Chen

ICCV 2025 · Label-efficient and robust learning › Recognition and long-tail · approach: Dense features and foundation priors · 13 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 2k synthetic samples to small real training set (8k)VAD · Waymo val open-loopplanning L2 avg / CR avg: 1.39 -> 1.18; 0.52 -> 0.45Improved
add 2k synthetic samples to larger real training set (28k)VAD · Waymo val open-loopplanning L2 avg / CR avg: 1.09 -> 1.04; 0.32 -> 0.25Improved
add adaptive kinematic model instead of bicycle model (ablation)Scene Controller · Waymo reconstructed scenes, VAD proxyplanning L2 @3s (m): 2.43 -> 2.06Improved
add adaptive kinematic model instead of bicycle model (ablation)Scene Controller · Waymo reconstructed scenes, VAD proxyMapSeg AP 0.5: 0.170 -> 0.185Improved
add 3DRealCar assets with directional shadows instead of virtual vehicle assetsScene Renderer · Waymo reconstructed scenesCar AP: 38.4 -> 39.6Improved
replace real foreground and background by rendered scene (3DRealCar Rep.)VAD perception · Waymo reconstructed scenesCar AP: 44.1 -> 39.6Hurt
fine-tune with 6k synthetic samplesVAD · Closed-loop unseen scenesroute completion / vehicle collision: 42.01 -> 53.03; 7.55 -> 3.43Improved
fine-tune with 6k synthetic samplesGenAD · Closed-loop unseen scenesroute completion / vehicle collision: 44.87 -> 49.65; 7.62 -> 5.45Improved
fine-tune with synthetic data on turn scenesVAD · Closed-loop unseen scenes (turn)route completion: 25.71 -> 34.72Improved
fine-tune with synthetic data on reconstructed training scenesVAD · Closed-loop reconstructed scenesroute completion: 29.88 -> 39.02Improved
add bidirectional interaction to synthetic trafficScene Controller · Waymo scenesinteraction rateImproved

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