A multi-task network predicts degradation patterns and a multiplicative Global Sensor Health Index from RGB images to provide early warnings of camera failure in autonomous driving before downstream detection degrades.
DAWN: Vehicle detection in adverse weather nature dataset
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
fields
cs.CV 5verdicts
UNVERDICTED 5representative citing papers
IA-CLAHE trains a lightweight network on a differentiable CLAHE extension to predict per-tile clip limits that drive local histograms toward a uniform distribution, delivering zero-shot gains in recognition accuracy and visual quality.
A diffusion framework decomposes images into intrinsic maps via an inverse renderer and renders controllable weather changes via a forward renderer with CLIP prompt interpolation and map-aware attention, outperforming pixel-space baselines on new 38k synthetic and 18k real datasets.
CADENet introduces an asynchronous dual-stream enhancement network with CAPE and EG-NMS plus CLIP zero-shot classification to improve camera-based detection in rain, fog, snow and sand without retraining or latency penalty, reporting low F1 scores on DAWN as lower bounds due to annotation bias.
WeatherRemover is a lightweight all-in-one adverse weather removal model that uses channel-wise attention, linear spatial reduction, and gating in a multi-scale transformer-UNet to restore images efficiently across rain, snow, and fog.
citing papers explorer
-
Safety-Critical Camera Reliability Monitoring for ADAS via Degradation-Aware Uncertainty Pattern Analysis
A multi-task network predicts degradation patterns and a multiplicative Global Sensor Health Index from RGB images to provide early warnings of camera failure in autonomous driving before downstream detection degrades.
-
IA-CLAHE: Image-Adaptive Clip Limit Estimation for CLAHE
IA-CLAHE trains a lightweight network on a differentiable CLAHE extension to predict per-tile clip limits that drive local histograms toward a uniform distribution, delivering zero-shot gains in recognition accuracy and visual quality.
-
IntrinsicWeather: Controllable Weather Editing in Intrinsic Space
A diffusion framework decomposes images into intrinsic maps via an inverse renderer and renders controllable weather changes via a forward renderer with CLIP prompt interpolation and map-aware attention, outperforming pixel-space baselines on new 38k synthetic and 18k real datasets.
-
CADENet: Condition-Adaptive Asynchronous Dual-Stream Enhancement Network for Adverse Weather Perception in Autonomous Driving
CADENet introduces an asynchronous dual-stream enhancement network with CAPE and EG-NMS plus CLIP zero-shot classification to improve camera-based detection in rain, fog, snow and sand without retraining or latency penalty, reporting low F1 scores on DAWN as lower bounds due to annotation bias.
-
WeatherRemover: All-in-one Adverse Weather Removal with Multi-scale Feature Map Compression
WeatherRemover is a lightweight all-in-one adverse weather removal model that uses channel-wise attention, linear spatial reduction, and gating in a multi-scale transformer-UNet to restore images efficiently across rain, snow, and fog.