IDM-Net is a lightweight Illumination-Decoupled Modulation Network designed for low-light image enhancement. It uses a dual-encoder architecture: a structure encoder extracts multi-scale appearance features from the RGB image, while a lightweight illumination encoder learns illumination priors from the decoupled luminance channel. An Illumination-Guided Modulation module injects these priors into the decoder via spatially adaptive affine modulation, and a Feature Refinement Block progressively suppresses artifacts and recovers fine details, achieving competitive performance on standard benchmarks with good balance between quality and efficiency.
By Cheng-Yen Hsiao, Jing-Ming Guo
arXiv:2608.29243v1 Announce Type: new
Abstract: Existing diffusion-based enhancement methods provide strong generative capability for low-light image enhancement (LLIE), yet they either rely on paire...
By Wenjie Cai, Yuezhe Yang, Jianyang Xia, Xingbo Dong, Zhe Jin
arXiv:2608.21847v1 Announce Type: new
Abstract: Low-light image enhancement (LLIE) must correct ambiguous exposure without overwriting structure already supported by the input. Generative transport c...
By Yi Ai, Zheng Chen, Yuanhao Cai, Yulun Zhang, Xiaokang Yang
Consist‑Retinex introduces a one‑step noise‑emphasized consistency training framework for Retinex‑based low‑light image enhancement. It first decomposes images into reflectance and illumination maps using a Retinex Transformer Decomposition Network, then trains two conditional consistency models with a dual objective that blends trajectory consistency and ground‑truth alignment. The method employs adaptive noise‑emphasized fixed‑point sampling to focus supervision near the inference endpoint, achieving state‑of‑the‑art VE‑LOL‑L scores on paired and unpaired low‑light benchmarks while reducing sampling and training costs.
By Jian Xu, Wei Chen, Shigui Li, Delu Zeng, John Paisley, Qibin Zhao
The paper introduces PRIN, a Perceptual-Structural Retinex-Inspired Network designed for low‑light image enhancement. PRIN uses a shared encoder with asymmetric decoders to separately refine reflectance and illumination components, applying attention‑guided wavelet refinement for textures and edge preservation in the reflectance branch and spatially coherent brightness adjustment in the illumination branch. A curve‑based post‑composition head further corrects tone and exposure, achieving state‑of‑the‑art SSIM, LPIPS, and PSNR results on multiple LOL datasets.
By Qiyi Xie, Wei Chen Ng, Ziyao Li, Yuning Wu, Huasen Wu, Tianshi Miao, Jian Ding Tan
The paper introduces 3L-Dataset, a physically calibrated low‑light image and video dataset created with a modular, sensor‑agnostic acquisition framework. The test bench reproduces the Midavaine night‑level scale from full moon to overcast moonless night, covering visible to near‑infrared spectra across varied environments while ensuring sub‑pixel alignment across synchronized image sextuplets. The authors evaluate deep‑learning baselines on this dataset, highlighting trade‑offs between reconstruction fidelity, perceptual quality, and inference latency under severe photon starvation.
arXiv:2610.28191v1 Announce Type: new
Abstract: Incorrect exposure degrades both image brightness and recoverable scene detail. Existing sRGB-based correction methods are limited by the non-linear im...
By Yingkai Zhang, Yunhao Zou, Ying Fu
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...
Low-light image enhancement algorithms (LIEAs) aim to improve the visibility of images captured under poor illumination. However, the enhancement process often introduces artifacts such as noise amplification, color shift, structural damage, and over-exposure, which degrade the perceptual quality of the enhanced images.
GLOW-FM is a one‑step latent flow‑matching framework designed for efficient generative low‑light image enhancement (LLIE). It operates in the latent space of a frozen Tiny‑VAE, using Terminal Velocity Matching (TVM) to achieve high‑quality enhancement with a single function evaluation. Experiments on real‑world benchmarks show competitive image quality, strong cross‑dataset generalization, and low computational cost (34 GFLOPs for the small variant).
By Ariel Lapid, Yuval Haitman, Reuven Peretz, Arnon Netzer, Idit Diamant
arXiv:2610.33402v1 Announce Type: new
Abstract: Existing Ultra-High-Definition (UHD) low-light image enhancement (LLIE) methods typically rely on either spatial- or frequency-domain modeling, or inde...
By Bo Fu, Hai Chi, Liyan Wang, Shilin Fu, Wei Wang, Kin-Man Lam, Jinshan Pan, Cong Wang
arXiv:2611.07665v1 Announce Type: new
Abstract: Capturing scenes with extreme motion and high dynamic range is fundamentally constrained by trade-offs among temporal resolution, spatial detail, signa...
By Yapeng Meng, Yuguo Chen, Xiangru Chen, Shaojun Xu, Xuezhen Wang, Lijian Wang, Zheyu Yang, Yihan Lin, Luping Shi, Rong Zhao