DreamStream: Towards Policy-Oriented Generative Simulation for End-to-End Driving
Ranking
Overall
80
Content
95
Popularity
44
Observed public metrics from 1 member.
Merged summary
TL;DR - DreamStream is a generative closed-loop driving simulator designed to preserve policy-relevant scene features rather than optimize photorealism alone. It enables more faithful testing and reveals policy failures missed by prior benchmarks.
- Distills a pretrained autoregressive video model using traffic-layout guidance to vary appearance while preserving scene geometry and dynamic-object consistency.
- Introduces FDπ, a Fréchet-distance metric based on scene-context features from public end-to-end driving policies, addressing shortcomings of metrics such as FID.
- Improves FDπ over the strongest prior closed-loop simulator by 1.6× on nuScenes and 4.7× on NAVSIM.
- Builds Navhard-CL, an interactive benchmark with adversarial driving and weather variations that exposes scorer bias and weak recovery behavior.
Sources (1)
DreamStream: Towards Policy-Oriented Generative Simulation for End-to-End Driving
Public signals
Semantic Scholar citations 1 · Semantic Scholar influential citations 0
TL;DR - DreamStream is a generative closed-loop driving simulator designed to preserve policy-relevant scene features rather than optimize photorealism alone. It enables more faithful testing and reveals policy failures missed by prior benchmarks.
- Distills a pretrained autoregressive video model using traffic-layout guidance to vary appearance while preserving scene geometry and dynamic-object consistency.
- Introduces FDπ, a Fréchet-distance metric based on scene-context features from public end-to-end driving policies, addressing shortcomings of metrics such as FID.
- Improves FDπ over the strongest prior closed-loop simulator by 1.6× on nuScenes and 4.7× on NAVSIM.
- Builds Navhard-CL, an interactive benchmark with adversarial driving and weather variations that exposes scorer bias and weak recovery behavior.