Illumination-Adaptive Unpaired Low-Light Enhancement

Kandula, Praveen; Suin, Maitreya; Rajagopalan, A. N.

doi:10.1109/tcsvt.2023.3241162

Cited by 7 publications

(5 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…LE-Net [ 34 ] achieved efficient DL-based enhancement in driving scenarios and can be used in extremely dark conditions. AugGAN [ 35 ] and IA-GAN [ 36 ] have both acquired knowledge of simulated lighting conditions, using GAN models for all-day driving environment data simulation, making their enhancement networks adaptable to multiple detectors. Regarding efficient computation, according to the authors of [ 37 ], the current Swin Transformer-based methods can perform calculations with as low as 90k parameters and a computation time of 0.004 s, significantly lower than the processing time of traditional methods, thereby creating a faster response time for real-time hazard avoidance in vehicles.…”

Section: Literature Reviewmentioning

confidence: 99%

VELIE: A Vehicle-Based Efficient Low-Light Image Enhancement Method for Intelligent Vehicles

Ye,

Wang,

Yang

et al. 2024

Sensors

View full text Add to dashboard Cite

In Advanced Driving Assistance Systems (ADAS), Automated Driving Systems (ADS), and Driver Assistance Systems (DAS), RGB camera sensors are extensively utilized for object detection, semantic segmentation, and object tracking. Despite their popularity due to low costs, RGB cameras exhibit weak robustness in complex environments, particularly underperforming in low-light conditions, which raises a significant concern. To address these challenges, multi-sensor fusion systems or specialized low-light cameras have been proposed, but their high costs render them unsuitable for widespread deployment. On the other hand, improvements in post-processing algorithms offer a more economical and effective solution. However, current research in low-light image enhancement still shows substantial gaps in detail enhancement on nighttime driving datasets and is characterized by high deployment costs, failing to achieve real-time inference and edge deployment. Therefore, this paper leverages the Swin Vision Transformer combined with a gamma transformation integrated U-Net for the decoupled enhancement of initial low-light inputs, proposing a deep learning enhancement network named Vehicle-based Efficient Low-light Image Enhancement (VELIE). VELIE achieves state-of-the-art performance on various driving datasets with a processing time of only 0.19 s, significantly enhancing high-dimensional environmental perception tasks in low-light conditions.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

VELIE: A Vehicle-Based Efficient Low-Light Image Enhancement Method for Intelligent Vehicles

Ye,

Wang,

Yang

et al. 2024

Sensors

View full text Add to dashboard Cite

show abstract

“…This method achieves low-light image enhancement by utilizing adaptive feature selection and attention that can perceive global and local details. Kandula et al [ 16 ] proposed a low-light image-enhancement method for adaptive lighting. This method addresses the issue of insufficient enhancement under various lighting conditions by introducing an illumination adaptive-enhancement network.…”

Section: Related Workmentioning

confidence: 99%

“…Kandula [16] Enhance images in two stages with a context-guided adaptive canonical unsupervised enhancement network.…”

Section: Prien [12]mentioning

confidence: 99%

“…Based on this, researchers attempted to improve low-light images using an alternative, unsupervised approach. Kandula et al [16] proposed a low-light image-enhancement method for adaptive lighting. This method addresses the issue of insufficient enhancement under various lighting conditions by introducing an illumination adaptive-enhancement network.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Cyclic Generative Attention-Adversarial Network for Low-Light Image Enhancement

Zhen,

Peng,

2023

Sensors

View full text Add to dashboard Cite

Images captured under complex conditions frequently have low quality, and image performance obtained under low-light conditions is poor and does not satisfy subsequent engineering processing. The goal of low-light image enhancement is to restore low-light images to normal illumination levels. Although many methods have emerged in this field, they are inadequate for dealing with noise, color deviation, and exposure issues. To address these issues, we present CGAAN, a new unsupervised generative adversarial network that combines a new attention module and a new normalization function based on cycle generative adversarial networks and employs a global–local discriminator trained with unpaired low-light and normal-light images and stylized region loss. Our attention generates feature maps via global and average pooling, and the weights of different feature maps are calculated by multiplying learnable parameters and feature maps in the appropriate order. These weights indicate the significance of corresponding features. Specifically, our attention is a feature map attention mechanism that improves the network’s feature-extraction ability by distinguishing the normal light domain from the low-light domain to obtain an attention map to solve the color bias and exposure problems. The style region loss guides the network to more effectively eliminate the effects of noise. The new normalization function we present preserves more semantic information while normalizing the image, which can guide the model to recover more details and improve image quality even further. The experimental results demonstrate that the proposed method can produce good results that are useful for practical applications.

show abstract

“…Learning-based deep networks give impressive results for individual restoration tasks like deblurring [10]- [25], dehazing [26]- [29], inpainting [30], [31], enhancement [32], [33], superresolution [34]- [40], bokeh rendering [41], inpainting [31], [42] etc. Unsupervised methods relax the need for paired datasets for training a deep net.…”

Section: Introduction and Related Workmentioning

confidence: 99%

Distortion Disentanglement and Knowledge Distillation for Satellite Image Restoration

Kandula

Rajagopalan

2022

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Satellite images are typically subject to multiple distortions. Different factors affect the quality of satellite images, including changes in atmosphere, surface reflectance, sun illumination, viewing geometries etc., limiting its application to downstream tasks. In supervised networks, the availability of paired datasets is a strong assumption. Consequently, many unsupervised algorithms have been proposed to address this problem. These methods synthetically generate a large dataset of degraded images using image formation models. A neural network is then trained with an adversarial loss to discriminate between images from distorted and clean domains. However, these methods yield suboptimal performance when tested on real images that do not necessarily conform to the generation mechanism. Also, they require a large amount of training data and are rendered unsuitable when only a few images are available. We propose a distortion disentanglement and knowledge distillation framework for satellite image restoration to address these important issues. Our algorithm requires only two images: the distorted satellite image to be restored and a reference image with similar semantics. Specifically, we first propose a mechanism to disentangle distortion. This enables us to generate images with varying degrees of distortion using the disentangled distortion and the reference image. We then propose the use of knowledge distillation to train a restoration network using the generated image pairs. As a final step, the distorted image is passed through the restoration network to get the final output. Ablation studies show that our proposed mechanism successfully disentangles distortion. Exhaustive experiments on different timestamps of Google-Earth images and publicly available datasets, LEVIR-CD and SZTAKI, show that our proposed mechanism can tackle a variety of distortions and outperforms existing state-of-the-art restoration methods visually as well as on quantitative metrics.

show abstract

Illumination-Adaptive Unpaired Low-Light Enhancement

Cited by 7 publications

References 53 publications

VELIE: A Vehicle-Based Efficient Low-Light Image Enhancement Method for Intelligent Vehicles

VELIE: A Vehicle-Based Efficient Low-Light Image Enhancement Method for Intelligent Vehicles

Cyclic Generative Attention-Adversarial Network for Low-Light Image Enhancement

Distortion Disentanglement and Knowledge Distillation for Satellite Image Restoration

Contact Info

Product

Resources

About