Skip to content
Open access

Toward Realistic Low-Light Image Enhancement via ISP-Driven Data Modeling

Sep 2026 · IEEE Transactions on Image Processing · Vol 35, pp. 10697-10712 · 0 citations · 94 references
Medicine Computer Science

TL;DR

This paper proposes an image signal processing (ISP)-driven data synthesis pipeline that addresses challenges by generating scalable paired training data and applies it to existing LLIE methods, demonstrating its impact on improving their practicality and generalizability in real-world applications.

Abstract

Deep neural networks (DNNs) have recently become the leading method for low-light image enhancement (LLIE). However, despite significant progress, their outputs may still exhibit issues such as amplified noise, incorrect white balance, or unnatural enhancements when deployed in real-world applications. A key challenge is the lack of diverse, large-scale training data that captures the complexities of low-light conditions and imaging pipelines. In this paper, we propose an image signal processing (ISP)-driven data synthesis pipeline that addresses these challenges by generating scalable paired training data. Specifically, our pipeline begins with easily collected high-quality normal-light images, which are first unprocessed into a pseudo-RAW representation using a reverse ISP. We then synthesize low-light degradations directly in this RAW-like domain. The resulting data are subsequently processed through a series of ISP stages, including white balance adjustment, color space conversion, tone mapping, and gamma correction, with controlled variations introduced at each stage. This broadens the degradation space and enhances the diversity of the training data. To demonstrate the effectiveness of the synthetic data, we conduct extensive experiments using a vanilla U-Net model consisting solely of convolutional layers, group normalization, GeLU activation, and convolutional block attention modules (CBAMs). Extensive testing across multiple datasets reveals that the vanilla U-Net model trained with our data synthesis pipeline delivers high-fidelity, visually appealing enhancement results. Additionally, we apply our pipeline to existing LLIE methods, demonstrating its impact on improving their practicality and generalizability in real-world applications. Our codes are publicly available at https://github.com/wzhsysu/LLIE

Read PDF

Similar papers

Preprint Oct 2026

MESS: Multi-Exposure Sequence Synthesis for Generalizable Image Enhancement

Despite the significant progress in image enhancement under adverse illuminations, such as low-light image enhancement, exposure correction, and backlit image enhancement, existing models show limited generalizability to different scenarios. A major bottleneck lies in the lack of large-scale and diverse training data,...

Ruo-Dai Cui, Shuai Liu, R. Wu et al. · 0 citations
Open access Oct 2026

Dynamic Interpolation for Training-Time Prediction Reshaping in Low-Light Image Enhancement

A Dynamic Interpolation Training-only Module (DITM), which introduces no additional learnable parameters and adaptively reshapes the model prediction for supervised feed-forward LLIE training, and improves fidelity and perceptual quality while preserving the inference-time architecture and introducing no additional inf...

Pei-Rui Zhu, Shi-Jie Hao, Jing-Xi Liao et al. · 0 citations
Preprint Nov 2026

3L-D: A Low-Light Level Dataset from a Sensor-Agnostic, Alignment-Preserving Acquisition Framework

Supervised low-light image and video enhancement has achieved remarkable progress, yet current models remain fundamentally constrained by the limitations of existing datasets. Prevailing methods typically rely on uncontrolled ambient captures, camera parameter manipulation (e.g., exposure or ISO adjustments), or neutra...

Léo Rueff, Maurgène Ghezal, V. Gorse et al. · 0 citations
Oct 2026

Ultra-High-Definition Image Restoration via Prior-driven Patch Bilateral Compensation

This work proposes Prior-driven Patch-based Bilateral Compensation (P2BiC), a memory-efficient UHD restoration framework that processes UHD images as patches via an in-network feature-space cropping computation path while maintaining global coherence.

Ze-Yu Xiao, Yang Zhao, Yu Liu et al. · 0 citations
Conference Open access Oct 2026

LumiNet: A Joint Single-Stage Compact CNN for Low-Light Image Enhancement and Denoising

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 · 0 citations
Preprint Oct 2026

Stabilizing Illumination Conditioning in SSM-Based Low-Light Image Enhancement with Bottleneck Prompt Sidecars

Low-light image enhancement (LLIE) requires more than brightness amplification because real low-light images often exhibit spatially varying illumination, amplified noise, color distortion, and local detail loss. Recent SSM- and Mamba-based restorers provide efficient long-range modeling, yet the route for introducing...

Wei-Chen Ng, Qi-Yi Xie, Jian-Ding Tan et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.