Related papers: TPCNet: Triple physical constraints for Low-light …
Recent advances in neural rendering have achieved impressive results on photorealistic shading and relighting, by using a multilayer perceptron (MLP) as a regression model to learn the rendering equation from a real-world dataset. Such…
Retinex-based low-light image enhancement benefits from separating reflectance and illumination, yet recent generative approaches often rely on iterative sampling and are difficult to deploy under strict latency budgets. Consistency models…
Low-light image enhancement aims to restore the under-exposure image captured in dark scenarios. Under such scenarios, traditional frame-based cameras may fail to capture the structure and color information due to the exposure time…
Although deep learning based models for underwater image enhancement have achieved good performance, they face limitations in both lightweight and effectiveness, which prevents their deployment and application on resource-constrained…
Humans' innate ability to decompose scenes into objects allows for efficient understanding, predicting, and planning. In light of this, Object-Centric Learning (OCL) attempts to endow networks with similar capabilities, learning to…
Low-light image enhancement is challenging due to complex degradations, including amplified noise, artifacts, and color distortion. While Retinex-based deep learning methods have achieved promising results, they primarily rely on…
Image captured under low-light conditions presents unpleasing artifacts, which debilitate the performance of feature extraction for many upstream visual tasks. Low-light image enhancement aims at improving brightness and contrast, and…
Low-light images suffer from severe noise and low illumination. Current deep learning models that are trained with real-world images have excellent noise reduction, but a ratio parameter must be chosen manually to complete the enhancement…
Image decomposition offers deep insights into the imaging factors of visual data and significantly enhances various advanced computer vision tasks. In this work, we introduce a novel approach to low-light image enhancement based on…
This paper introduces a novel approach to illumination manipulation in diffusion models, addressing the gap in conditional image generation with a focus on lighting conditions. We conceptualize the diffusion model as a black-box image…
Deep networks for computer vision are not reliable when they encounter adversarial examples. In this paper, we introduce a framework that uses the dense intrinsic constraints in natural images to robustify inference. By introducing…
The problem of high-dimensional and large-scale representation of visual data is addressed from an unsupervised learning perspective. The emphasis is put on discrete representations, where the description length can be measured in bits and…
Exposure correction methods aim to adjust the luminance while maintaining other luminance-unrelated information. However, current exposure correction methods have difficulty in fully separating luminance-related and luminance-unrelated…
Low-light image enhancement is a challenging low-level computer vision task because after we enhance the brightness of the image, we have to deal with amplified noise, color distortion, detail loss, blurred edges, shadow blocks and halo…
Under challenging light conditions, captured images often suffer from various degradations, leading to a decline in the performance of vision-based applications. Although numerous methods have been proposed to enhance image quality, they…
Low-light image enhancement (LLIE) aims to improve illumination while preserving high-quality color and texture. However, existing methods often fail to extract reliable feature representations due to severely degraded pixel-level…
Perceptual losses have emerged as powerful tools for training networks to enhance Low-Dose Computed Tomography (LDCT) images, offering an alternative to traditional pixel-wise losses such as Mean Squared Error, which often lead to…
Night images suffer not only from low light, but also from uneven distributions of light. Most existing night visibility enhancement methods focus mainly on enhancing low-light regions. This inevitably leads to over enhancement and…
In this paper, we propose a constrained linear data-feature mapping model as an interpretable mathematical model for image classification using convolutional neural network (CNN) such as the ResNet. From this viewpoint, we establish the…
Many learning-based low-light image enhancement (LLIE) algorithms are based on the Retinex theory. However, the Retinex-based decomposition techniques in such models introduce corruptions which limit their enhancement performance. In this…