Unified RAW Image Exposure Correction and Restoration via Linear Illumination and Frequency-Adaptive Enhancement

Yingkai Zhang; Yunhao Zou; Ying Fu

cs.CVOct 20, 2026

Unified RAW Image Exposure Correction and Restoration via Linear Illumination and Frequency-Adaptive Enhancement

Authors: Yingkai Zhang, Yunhao Zou, Ying Fu

Organizations: School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China

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.

Figures & tables

Panel of Figure 1 — Fig. 1: The RAW/sRGB images of indoor/outdoor scenes under different lighting conditions. Due to the limited dynamic range of the camera, the 8-bit sRGB output loses significant information from the scene under high-light conditions. The stamens of the white flowers are almost invisible in the sRGB image but are visible in the 14-bit RAW image. Due to the low signal-to-noise (SNR) and low signal intensity under low-light conditions, the sRGB image loses considerable detail. The tail of Pikachu and the edge of the box are essentially unrecognizable in the sRGB image, whereas they are discernible in the RAW image (Zoom in for better details).

Panel of Figure 2 — Fig. 2: Frequency analysis after linear scaling. (a–c) Scaled images, (d–f) high-frequency ( HF ) components, and (g–i) low-frequency ( LF ) components. Over-exposure removes edges, whereas under-exposure amplifies noise. Under different lighting conditions, the low-frequency information is similar to that in the reference image, indicating that information such as illumination remains essentially unchanged after linear adjustment.

Fig. 3: The overview framework of the proposed method (RIECR), including Linear Illumination Correction Network (LICN) to adjust the illumination and Frequency-based Enhancement Network (FEN) to address the divergent degradation.

Task	Dataset	Format	Type	Size	High	High-light Exposure Value	Low	Low-light Exposure Value	Normal-light Ground-Truth
Under-Exposure Correction	LOL [ 66 ]	sRGB	Real	789	✘	N/A	✓	N/A	✓
Under-Exposure Correction	LOL-v2 [ 66 ]	sRGB	Real	500	✘	N/A	✓	N/A	✓
(RAW Image Denoising)	SID [ 18 ]	RAW	Real	2,697	✘	N/A	✓	Ratio= $\frac{1}{100}$ , $\frac{1}{250}$ , $\frac{1}{300}$	✓
Over-Exposure Correction	RPO [ 9 ]	RAW	Real	2,600	✓	Ratio=3, 5, 8, 10	✘	N/A	✓
HDR Reconstruction	SIHDR [ 22 ]	RAW	Real	905	✓	N/A	✓	N/A	✘
Multiple-Exposure Correction	SICE [ 67 ]	sRGB	Real	4,413	✓	EV=0.5,0.7,1,2,3	✓	EV=-0.5,-0.7,-1,-2,-3	✓

TABLE I: Comparison of datasets for exposure correction and restoration tasks.

Fig. 4: Overview and analysis of the proposed CMER dataset. (a) Paired Samples: Representative scenes demonstrating rigorous alignment across extreme exposure ratios (from $1/32$ to $8$ ) and their normal-light ground truth. (b) Data Integrity: Histogram comparison confirming that the RAW data preserves the original linear response compared to processed sRGB formats [ 10 ] . (c) Dataset Diversity: Statistical comparison showing CMER provides broader scene coverage than the existing SIHDR [ 22 ] .

Methods	CMER (train) $\rightarrow$ CMER (test)						SMIT(pre) $\rightarrow$ CMER(ft) $\rightarrow$ CMER(test)						Params. (M)	MACs (G)
	High-light		Low-light		Average		High-light		Low-light		Average
	PSNR $\uparrow$	SSIM $\uparrow$	PSNR $\uparrow$	SSIM $\uparrow$	PSNR $\uparrow$	SSIM $\uparrow$	PSNR $\uparrow$	SSIM $\uparrow$	PSNR $\uparrow$	SSIM $\uparrow$	PSNR $\uparrow$	SSIM $\uparrow$
sRGB-based Model
MSEC [ 10 ] [CVPR’21]	26.72	0.875	25.23	0.824	25.79	0.843	25.72	0.857	26.46	0.836	26.18	0.844	7.02	10.57
ECCM [ 71 ] [BMVC’21]	28.81	0.913	31.84	0.920	30.07	0.917	30.92	0.943	31.65	0.926	31.38	0.933	5.39	9.55
ECLNet [ 12 ] [MM’22]	26.76	0.899	26.89	0.876	26.76	0.885	29.08	0.929	26.99	0.890	27.77	0.905	0.02	1.67

TABLE II: Results on the disjoint CMER test split under two training protocols. Parameters and MACs are reported in M and G, respectively, with MACs calculated on a

256\times 256

RAW patch. Best and second-best restoration scores are bold and underlined .

Panel of Figure 7 — Fig. 5: CMER visual comparison for over-exposure (top) and under-exposure (bottom), displayed using the same RAW-to-sRGB ISP.

Panel of Figure 8 — Fig. 6: Comparison of illumination correction by the LICN in our model. The term w/o Guidance indicates adjustment without separating the color channels, w/o Label means adjustment without estimating the illumination label, w/o Linear means adjustment without linear operation, instead of an illumination map that is added to the original image.

LICN	FEN	High-light		Low-light		Average
LICN	FEN	PSNR $\uparrow$	SSIM $\uparrow$	PSNR $\uparrow$	SSIM $\uparrow$	PSNR $\uparrow$	SSIM $\uparrow$
✘	✘	26.35	0.894	27.61	0.825	27.13	0.851
✓	✘	29.90	0.950	30.67	0.808	30.38	0.861
✘	✓	30.07	0.939	31.37	0.931	30.88	0.934
✓	✓	31.23	0.950	33.45	0.950	32.63	0.950

TABLE III: Ablation of the proposed RIECR framework.

Methods	High-light		Low-light		Average
Methods	PSNR $\uparrow$	SSIM $\uparrow$	PSNR $\uparrow$	SSIM $\uparrow$	PSNR $\uparrow$	SSIM $\uparrow$
LICN variants
w/o Linear	30.47	0.924	30.22	0.913	30.31	0.917
w/o Label	31.68	0.944	32.43	0.920	32.15	0.929
w/o Guidance	30.10	0.940	31.88	0.937	31.21	0.938
FEN variants

TABLE IV: Component ablation of LICN and FEN.

Panel of Figure 11 — Fig. 7: Visual quality comparison of FEN. Local and Global mean the local convolution branch and global attention branch, respectively.

Panel of Figure 12 — Fig. 8: FDC features in the first global-branch layer: (a,d) FDC input/output, (b,e) decomposed low/high frequencies, and (c,f) standard-convolution input/output. FDC retains structure while isolating residual detail.

Setting	High-light		Low-light		Average
Setting	PSNR $\uparrow$	SSIM $\uparrow$	PSNR $\uparrow$	SSIM $\uparrow$	PSNR $\uparrow$	SSIM $\uparrow$
sRGB	27.14	0.911	29.00	0.902	28.35	0.905
RAW	29.43	0.925	29.73	0.915	29.62	0.919

TABLE V: sRGB versus RAW input; metrics are evaluated in RGB.

Panel of Figure 14 — Fig. 9: The visualized comparison between the sRGB and RAW domains.

Panel of Figure 15 — Fig. 10: The visualized results for the cross-camera setting. The model is trained on Canon 5D IV and evaluated on the Sony IMX586 sensor.

Panel of Figure 16 — Fig. 11: Failure example for over-exposure areas. The histogram of the input data range indicates that some pixels are saturated.

Image Enhancement

Image enhancement restores visibility, color, detail, and dynamic range in degraded images for human viewing and downstream vision tasks.

See all 154 papers

Rethinking Exposure Correction for Spatially Non-uniform Degradation
Apr 5, 2026Ao Li, Jiawei Sun, Le Dong +2Image Enhancement
School of Artificial Intelligence, Xidian University, Xi’an, China · Hangzhou Institute of Technology, Xidian University, Hangzhou, China
AutoLumNet: Monotone Optimal Transport for Single-Shot Exposure Correction
Aug 20, 2026Airin Akter Tania, Md Raihan Khan, Mohiuddin AhmadImage Enhancement Low-Light Image Enhancement
Department of Electrical and Electronic Engineering (EEE) Khulna University of Engineering & Technology (KUET), Bangladesh
RPBA-Net: An Interpretable Residual Pyramid Bilateral Affine Network for RAW-Domain ISP Enhancement
May 5, 2026Yucheng Xin, Wu Chen, Xiang Chen +7Image Enhancement Residual Learning
School of Information Science and Engineering, Shandong Normal University, Jinan, China · National University of Defense Technology, Changsha, China · Nanjing University of Science and Technology, Nanjing, China +2

Apr 5, 2026J/K move · Enter open · S save

Rethinking Exposure Correction for Spatially Non-uniform Degradation

Ao Li, Jiawei Sun, Le Dong, Zhenyu Wang+1

School of Artificial Intelligence, Xidian University, Xi’an, China · Hangzhou Institute of Technology, Xidian University, Hangzhou, China

Image Enhancement

Open paper AskPDF arXiv

Real-world exposure correction is fundamentally challenged by spatially non-uniform degradations, where diverse exposure errors frequently coexist within a single image. However, existing exposure correction methods are still largely developed under a predominantly uniform assumption. Architecturally, they typically rely on globally aggregated modulation signals that capture only the overall exposure trend. From the optimization perspective, conventional reconstruction losses are usually derived under a shared global scale, thus overlooking the spatially varying correction demands across regions. To address these limitations, we propose a new exposure correction paradigm explicitly designed for spatial non-uniformity. Specifically, we introduce a Spatial Signal Encoder to predict spatially adaptive modulation weights, which are used to guide multiple look-up tables for image transformation, together with an HSL-based compensation module for improved color fidelity. Beyond the architectural design, we propose an uncertainty-inspired non-uniform loss that dynamically allocates the optimization focus based on local restoration uncertainties, better matching the heterogeneous nature of real-world exposure errors. Extensive experiments demonstrate that our method achieves superior qualitative and quantitative performance compared with state-of-the-art methods. Code is available at https://github.com/FALALAS/rethinkingEC.

Abstract

Image Enhancement

Explore similar work

Rethinking Exposure Correction for Spatially Non-uniform Degradation

AutoLumNet: Monotone Optimal Transport for Single-Shot Exposure Correction

RPBA-Net: An Interpretable Residual Pyramid Bilateral Affine Network for RAW-Domain ISP Enhancement