Low-light images are a common phenomenon when taking photos in low-light environments with inappropriate camera equipment, leading to shortcomings such as low contrast, color distortion, uneven brightness, and high loss of detail. These shortcomings are not only subjectively annoying but also affect the performance of many computer vision systems. Enhanced low-light images can be better applied to image recognition, object detection and image segmentation. This paper proposes a novel RetinexDIP method to enhance images. Noise is considered as a factor in image decomposition using deep learning generative strategies. The involvement of noise makes the image more real, weakens the coupling relationship between the three components, avoids overfitting, and improves generalization. Extensive experiments demonstrate that our method outperforms existing methods qualitatively and quantitatively.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC9332408 | PMC |
| http://dx.doi.org/10.3390/s22155593 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
FusionU10: enhancing pedestrian detection in low-light complex tourist scenes through multimodal fusion.
Front Neurorobot
January 2025
School of Business, Lingnan University, Hong Kong, China.
With the rapid development of tourism, the concentration of visitor flows poses significant challenges for public safety management, especially in low-light and highly occluded environments, where existing pedestrian detection technologies often struggle to achieve satisfactory accuracy. Although infrared images perform well under low-light conditions, they lack color and detail, making them susceptible to background noise interference, particularly in complex outdoor environments where the similarity between heat sources and pedestrian features further reduces detection accuracy. To address these issues, this paper proposes the FusionU10 model, which combines information from both infrared and visible light images.
View Article and Find Full Text PDFDual-Modal Approach for Ship Detection: Fusing Synthetic Aperture Radar and Optical Satellite Imagery.
Sensors (Basel)
January 2025
Department of Electrical and Software Engineering, University of Calgary, Calgary, AB T2N 1N4, Canada.
The fusion of synthetic aperture radar (SAR) and optical satellite imagery poses significant challenges for ship detection due to the distinct characteristics and noise profiles of each modality. Optical imagery provides high-resolution information but struggles in adverse weather and low-light conditions, reducing its reliability for maritime applications. In contrast, SAR imagery excels in these scenarios but is prone to noise and clutter, complicating vessel detection.
View Article and Find Full Text PDFEnhancing Low-Light Images with Kolmogorov-Arnold Networks in Transformer Attention.
Sensors (Basel)
January 2025
Faculty of Electronics, Telecommunications and Information Technologies, Polytechnic University Timisoara, 300223 Timisoara, Romania.
Low-light image enhancement (LLIE) techniques improve the performance of image sensors by enhancing visibility and details in poorly lit environments and have significantly benefited from recent research into Transformer models. This work presents a novel Transformer attention mechanism inspired by the Kolmogorov-Arnold representation theorem, incorporating learnable non-linearity and multivariate function decomposition. This innovative mechanism is the foundation of KAN-T, our proposed Transformer network.
View Article and Find Full Text PDFWhen low-light meets flares: Towards Synchronous Flare Removal and Brightness Enhancement.
Neural Netw
January 2025
Hefei University of Technology, Hefei, 230601, China; The Key Laboratory of Knowledge Engineering with Big Data, Ministry of Education, Hefei, 230601, China.
Low-light image enhancement (LLIE) aims to improve the visibility and illumination of low-light images. However, real-world low-light images are usually accompanied with flares caused by light sources, which make it difficult to discern the content of dark images. In this case, current LLIE and nighttime flare removal methods face challenges in handling these flared low-light images effectively: (1) Flares in dark images will disturb the content of images and cause uneven lighting, potentially resulting in overexposure or chromatic aberration; (2) the slight noise in low-light images may be amplified during the process of enhancement, leading to speckle noise and blur in the enhanced images; (3) the nighttime flare removal methods usually ignore the detailed information in dark regions, which may cause inaccurate representation.
View Article and Find Full Text PDFRetina-Inspired Flexible Visual Synaptic Device for Dynamic Image Processing.
ACS Appl Mater Interfaces
January 2025
School of Physics, Beihang University, Beijing 100191, China.
Exploiting biomimetic perception of invisible spectra in flexible artificial human vision systems (HVSs) is crucial for real-time dynamic information processing. Nevertheless, the fast processing of motion objects in natural environments poses a challenge, necessitating that these artificial HVSs simultaneously have swift photoresponse and nonvolatile memory. Here, inspired by the human retina, we propose a flexible UV neuromorphic visual synaptic device (NeuVSD) based on GaO@GaN-composited nanowires for dynamic visual perception.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!