Related papers: Learning with Nested Scene Modeling and Cooperativ…

Adverse lighting conditions, such as cast shadows and irregular illumination, pose significant challenges to computer vision systems by degrading visibility and color fidelity. Consequently, effective shadow removal and ALN are critical for…

Lowering the radiation dose in computed tomography (CT) can greatly reduce the potential risk to public health. However, the reconstructed images from the dose-reduced CT or low-dose CT (LDCT) suffer from severe noise, compromising the…

The usage of digital content (photos and videos) in a variety of applications has increased due to the popularity of multimedia devices. These uses include advertising campaigns, educational resources, and social networking platforms. There…

This paper presents a novel and interpretable end-to-end learning framework, called the deep compensation unfolding network (DCUNet), for restoring light field (LF) images captured under low-light conditions. DCUNet is designed with a…

Routine visual inspections of concrete structures are imperative for upholding the safety and integrity of critical infrastructure. Such visual inspections sometimes happen under low-light conditions, e.g., checking for bridge health. Crack…

Differentiable Architecture Search (DARTS) has attracted a lot of attention due to its simplicity and small search costs achieved by a continuous relaxation and an approximation of the resulting bi-level optimization problem. However, DARTS…

Deep learning has become in recent years a cornerstone tool fueling key innovations in the industry, such as autonomous driving. To attain good performances, the neural network architecture used for a given application must be chosen with…

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…

Subspace learning is an important problem, which has many applications in image and video processing. It can be used to find a low-dimensional representation of signals and images. But in many applications, the desired signal is heavily…

Low-light image enhancement aims to improve the perception of images collected in dim environments and provide high-quality data support for image recognition tasks. When dealing with photos captured under non-uniform illumination, existing…

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…

Reinforcement learning (RL) is a goal-oriented learning solution that has proven to be successful for Neural Architecture Search (NAS) on the CIFAR and ImageNet datasets. However, a limitation of this approach is its high computational…

Large Neighborhood Search (LNS) is a universal approach that is broadly applicable and has proven to be highly efficient in practice for solving optimization problems. We propose to integrate machine learning (ML) into LNS to assist in…

Lensless cameras relax the design constraints of traditional cameras by shifting image formation from analog optics to digital post-processing. While new camera designs and applications can be enabled, lensless imaging is very sensitive to…

Inverse rendering seeks to recover 3D geometry, surface material, and lighting from captured images, enabling advanced applications such as novel-view synthesis, relighting, and virtual object insertion. However, most existing techniques…

Real-world low-light images often suffer from complex degradations such as local overexposure, low brightness, noise, and uneven illumination. Supervised methods tend to overfit to specific scenarios, while unsupervised methods, though…

Modern machine learning often relies on optimizing a neural network's parameters using a loss function to learn complex features. Beyond training, examining the loss function with respect to a network's parameters (i.e., as a loss…

Many computer vision systems require low-cost segmentation algorithms based on deep learning, either because of the enormous size of input images or limited computational budget. Common solutions uniformly downsample the input images to…

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…

Compared to abstract features, significant objects, so-called landmarks, are a more natural means for vehicle localization and navigation, especially in challenging unstructured environments. The major challenge is to recognize landmarks in…