Image intrinsic components guided conditional diffusion model for low-light image enhancement
Through formulating the image restoration as a generation problem, the conditional diffusion
model has been applied to low-light image enhancement (LIE) to restore the details in dark …
model has been applied to low-light image enhancement (LIE) to restore the details in dark …
An illumination-guided dual attention vision transformer for low-light image enhancement
Existing Retinex-based low-light image enhancement methods often overlook corruptions
hidden in darkness or pattern collapse caused by the lit-up process. Recent deep learning …
hidden in darkness or pattern collapse caused by the lit-up process. Recent deep learning …
Training-free prior guided diffusion model for zero-reference low-light image enhancement
Images captured under poor illumination not only struggle to provide satisfactory visual
information but also adversely affect high-level visual tasks. Therefore, we delve into low …
information but also adversely affect high-level visual tasks. Therefore, we delve into low …
FPGA-based low-light image enhancement using Retinex algorithm and coarse-grained reconfigurable architecture
Advancements in digital imaging and video processing are often challenged by low-light
environments, leading to degraded visual quality. This affects critical sectors such as …
environments, leading to degraded visual quality. This affects critical sectors such as …
LEFuse: Joint low-light enhancement and image fusion for nighttime infrared and visible images
M Cheng, H Huang, X Liu, H Mo, X Zhao, S Wu - Neurocomputing, 2025 - Elsevier
Infrared and visible image fusion (IVIF) aims to represent scenes more richly and accurately
by integrating information from both modalities. However, existing IVIF methods are typically …
by integrating information from both modalities. However, existing IVIF methods are typically …
A new method for fusing infrared and visible images in low-light environments based on visual perception and attention mechanism
Z Pei, J Lu, Y Qian, L Fan, H Wang, J Chen - Optics and Lasers in …, 2025 - Elsevier
The purpose of infrared and visible image fusion is to fully leverage the information from
these two distinct types of images to achieve high-quality information complementarity …
these two distinct types of images to achieve high-quality information complementarity …
ReFusion: Learning Image Fusion from Reconstruction with Learnable Loss Via Meta-Learning
Image fusion aims to combine information from multiple source images into a single one with
more comprehensive informational content. Deep learning-based image fusion algorithms …
more comprehensive informational content. Deep learning-based image fusion algorithms …