Sep 2026· International Conference on Frontiers of Applied Optics and Computer Engineering· Vol 14346, pp. 143460D - 143460D-6· 0 citations· 12 references
Engineering
TL;DR
This work improves the RAW domain high dynamic range (HDR) low-light image reconstruction algorithm based on the joint optimization of neural exposure field and low-rank denoising, and introduces a low-rank denoising module integrating non-local similarities.
Abstract
We improve the RAW domain high dynamic range (HDR) low-light image reconstruction algorithm based on the joint optimization of neural exposure field and low-rank denoising. We attempt to construct a sensor-specific RAW domain degradation model that improves the characterization of noise, underexposure, and dynamic range compression in real low-light scenes, and avoids information loss caused by ISP processing. Using the neural exposure field module, we build a model with variable exposure features in image space to achieve adaptive exposure adjustment and HDR expansion. We introduce a low-rank denoising module integrating non-local similarities, which uses the low-rank structure and redundant information of image blocks to preserve edge texture details and suppress Gaussian mixture noise. We jointly optimize the loss function to realize end-to-end collaborative optimization of exposure adjustment and denoising. Experiments on public datasets (SID, RAW-LOL) show that our algorithm achieves a PSNR of 32.67 dB and an SSIM of 0.945, with optimized quantitative metrics and visual effects. It effectively alleviates overexposure and underexposure in bright and dark areas, suitable for high-quality low-light imaging in professional photography and medical imaging.
We improve the RAW domain high dynamic range (HDR) low-light image reconstruction algorithm based on the joint optimization of neural exposure field, low-rank denoising, discrete wavelet transforms (DWT) and robust digital watermarking. We construct a sensor-specific RAW domain degradation model that improves the chara...
Guo-Quan Wang, Min-Chuan Huang· International Conference on...· 0 citations
This paper proposes a unified RAW Image Exposure Correction and Restoration (RIECR) framework for both under- and over-exposed images and builds a real paired RAW benchmark containing 223 scenes and 1,784 pairs covering complex multi-exposure errors.
Low-light image restoration remains a challenging problem due to poor illumination, colour distortion, structural detail loss, and amplified sensor noise. Existing restoration methods often rely on multi-stage enhancement and denoising pipelines that increase computational complexity and introduce error propagation dur...
Himidiri Himakanika Pushpakumara, Seyed Ruzaik· International Conference on...· 0 citations
The Efficient Dual Attention Fusion Network (EDAFNet), which combines CBAM-guided initialization, hierarchical local and global attention for cross-exposure alignment and fusion, and a lightweight refinement module based on depthwise separable convolutions, is presented.
Ian Teixeira, Q. Leher, Josue Lopez-Cabrejos et al.· Pattern Analysis and Applica...· 0 citations
Low-light images are degraded by uneven illumination, sensor noise, color distortion, and weak texture boundaries. To address insufficient detail recovery, noise amplification, and inadequate coordination between global illumination and local texture, this paper proposes MSFA-Net, a compact residual enhancement network...
Han Xu· International Journal of Com...· 0 citations
Low-light image enhancement aims to improve image quality under insufficient illumination while recovering underlying structural and texture information. Existing approaches, ranging from conventional image processing techniques to deep generative models, have shown promising performance in brightness enhancement and d...
Yao Lu, Jun-Liang Tan, Hai-Peng Liang et al.· Journal of King Saud Univers...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.