Raw image exposure correction improves brightness and details
Unified RAW Image Exposure Correction and Restoration via Linear Illumination and Frequency-Adaptive Enhancement
Computer Vision and Pattern Recognition
Summary
Photos can look too dark or too bright when the camera exposure is wrong, hiding details. The authors created a new way to fix these problems directly using the camera's raw image data before it gets processed. Their method fixes brightness with linear adjustments and cleans up leftover problems by handling different parts of the image separately. They also tested it on a large collection of real images with different exposure issues and found it works better than existing methods.
What this means in practice
- •For camera software developers: Improve image quality in digital cameras by automatically fixing both under- and over-exposure in raw photos before processing.$Commercial implications: Enables camera manufacturers to offer better exposure correction features directly in raw image pipelines, improving photo output across lighting conditions.
- •For photo editing software teams: Add advanced raw exposure correction tools that enhance brightness and recover details lost in poorly exposed images.
Authors
Yingkai Zhang, Yunhao Zou, Ying Fu
Abstract
Incorrect exposure degrades both image brightness and recoverable scene detail. Existing sRGB-based correction methods are limited by the non-linear image signal processing pipeline, whereas RAW-based methods are usually developed for a single degradation type, such as low-light denoising or high-light recovery. In this paper, we focus on joint exposure correction and restoration directly in the RAW domain and propose a unified RAW Image Exposure Correction and Restoration (RIECR) framework for both under- and over-exposed images. RIECR decomposes the problem into two coupled sub-problems that follow the RAW imaging model: linear illumination correction and residual degradation restoration. First, a Linear Illumination Correction Network (LICN) estimates exposure-aware linear gains by using channel-specific RAW cues. It exploits the high signal-to-noise ratio of Green channels for robust brightening and the relatively unsaturated Red/Blue responses for high-light darkening. Second, a dual-branch Frequency-based Enhancement Network (FEN) restores the remaining degradation with a Frequency Dynamic Convolution (FDC) module. FDC decomposes convolutional responses into low- and high-frequency components and adaptively suppresses amplified noise or recovers clipped textures according to the exposure context. We further build a real paired RAW benchmark containing 223 scenes and 1,784 pairs covering complex multi-exposure errors. Experiments against sixteen state-of-the-art methods show that RIECR achieves state-of-the-art performance on real RAW exposure correction.