arXiv AI
Cue-guided dual-path reconstruction with adaptive multi-scale response refinement for low-light image enhancement
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computer Vision
Sep 28
IDM-Net: A Lightweight Illumination-Decoupled Modulation Network for Low-Light Image Enhancement
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.
arXiv Computer Vision
Sep 1
DARD: Zero-Shot Degradation-Aware Retinex-Guided Diffusion for Low-Light Image Enhancement
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...
arXiv Computer Vision
Aug 25
BC-IHV: Conditioning the Color Space for Stable Rectified-Flow Low-Light Enhancement
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...
arXiv AI
Sep 28
Consist-Retinex: One-Step Noise-Emphasized Consistency Training Accelerates High-Quality Retinex Enhancement
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.
arXiv Computer Vision
4d ago
PRIN: A Perceptual-Structural Retinex-Inspired Network for Low-Light Image Enhancement
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.
Hugging Face Trending Papers
4d ago
3L-D: A Low-Light Level Dataset from a Sensor-Agnostic, Alignment-Preserving Acquisition Framework
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.