Related papers: Learning to See in the Extremely Dark

Activities in underwater environments are paramount in several scenarios, which drives the continuous development of underwater image enhancement techniques. A major challenge in this domain is the depth at which images are captured, with…

Intrinsic image decomposition is the process of recovering the image formation components (reflectance and shading) from an image. Previous methods employ either explicit priors to constrain the problem or implicit constraints as formulated…

Single-image relighting is a challenging task that involves reasoning about the complex interplay between geometry, materials, and lighting. Many prior methods either support only specific categories of images, such as portraits, or require…

Current methods for restoring underexposed images typically rely on supervised learning with paired underexposed and well-illuminated images. However, collecting such datasets is often impractical in real-world scenarios. Moreover, these…

This paper presents an algorithm that enhances undesirably illuminated images by generating and fusing multi-level illuminations from a single image.The input image is first decomposed into illumination and reflectance components by using…

Image compression at extremely low bitrates (below 0.1 bits per pixel (bpp)) is a significant challenge due to substantial information loss. In this work, we propose a novel two-stage extreme image compression framework that exploits the…

We present a learning-based technique for estimating high dynamic range (HDR), omnidirectional illumination from a single low dynamic range (LDR) portrait image captured under arbitrary indoor or outdoor lighting conditions. We train our…

We present a simple, yet effective diffusion-based method for fine-grained, parametric control over light sources in an image. Existing relighting methods either rely on multiple input views to perform inverse rendering at inference time,…

In multimedia application scenarios, images captured under low-illumination conditions often lead to lower accuracy in visual perception tasks compared to those taken in well-lit environments. To tackle this challenge, we propose AMIEOD, an…

The data bottleneck has emerged as a fundamental challenge in learning based image restoration methods. Researchers have attempted to generate synthesized training data using paired or unpaired samples to address this challenge. This study…

Images captured under low-light scenarios often suffer from low quality. Previous CNN-based deep learning methods often involve using Retinex theory. Nevertheless, most of them cannot perform well in more complicated datasets like LOL-v2…

In nighttime circumstances, it is challenging for individuals and machines to perceive their surroundings. While prevailing image restoration methods adeptly handle singular forms of degradation, they falter when confronted with intricate…

Existing low-light image enhancement (LIE) methods have achieved noteworthy success in solving synthetic distortions, yet they often fall short in practical applications. The limitations arise from two inherent challenges in real-world LIE:…

Though diffusion models have been successfully applied to various image restoration (IR) tasks, their performance is sensitive to the choice of training datasets. Typically, diffusion models trained in specific datasets fail to recover…

Imaging through dense fog presents unique challenges, with essential visual information crucial for applications like object detection and recognition obscured, thereby hindering conventional image processing methods. Despite improvements…

Existing methods for relightable view synthesis -- using a set of images of an object under unknown lighting to recover a 3D representation that can be rendered from novel viewpoints under a target illumination -- are based on inverse…

In this paper, we rethink the low-light image enhancement task and propose a physically explainable and generative diffusion model for low-light image enhancement, termed as Diff-Retinex. We aim to integrate the advantages of the physical…

Recent deep learning methods have achieved promising results in image shadow removal. However, their restored images still suffer from unsatisfactory boundary artifacts, due to the lack of degradation prior embedding and the deficiency in…

Single LDR to HDR reconstruction remains challenging for over-exposed regions where traditional methods often fail due to complete information loss. We present a training-free approach that enhances existing indirect and direct HDR…

Low-light image enhancement (LLIE) aims to improve low-illumination images. However, existing methods face two challenges: (1) uncertainty in restoration from diverse brightness degradations; (2) loss of texture and color information caused…