CADENet: Condition-Adaptive Asynchronous Dual-Stream Enhancement Network for Adverse Weather Perception in Autonomous Driving

ArXi:2605.19837v1 Announce Type: cross Adverse weather (rain, fog, sand, and snow) degrades camera-based object detection in autonomous vehicles. Existing enhancement-then-detect approaches stall the safety-critical perception loop, violating hard real-time requirements. Progress on this problem is also constrained by an under-recognized evaluation ceiling: ground truth annotated on degraded images cannot credit a detector that recovers objects the annotators themselves could not see, so a genuinely useful enhancement can register as a near-flat F1 gain.