Related papers: STAR: A Structure and Texture Aware Retinex Model

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…

Large-scale generative models have achieved remarkable advancements in various visual tasks, yet their application to shadow removal in images remains challenging. These models often generate diverse, realistic details without adequate…

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…

In this work, we propose a learning-based method to denoise and refine disparity maps of a given stereo method. The proposed variational network arises naturally from unrolling the iterates of a proximal gradient method applied to a…

Low-light image enhancement (LLE) aims to improve the visual quality of images captured in poorly lit conditions, which often suffer from low brightness, low contrast, noise, and color distortions. These issues hinder the performance of…

Detection Transformer (DETR) is a Transformer architecture based object detection model. In this paper, we demonstrate that it can also be used as a data augmenter. We term our approach as DETR assisted CutMix, or DeMix for short. DeMix…

In this paper the use of Random Sprays Retinex (RSR) algorithm for global illumination estimation is proposed and its feasibility tested. Like other algorithms based on the Retinex model, RSR also provides local illumination estimation and…

Contamination from stars in the galaxy samples of large-scale structure surveys can bias cosmological constraints if not tightly controlled. This is especially true for lens samples used for galaxy clustering and galaxy-galaxy lensing…

We propose STARS, a randomized derivative-free algorithm for unconstrained optimization when the function evaluations are contaminated with random noise. STARS takes dynamic, noise-adjusted smoothing step-sizes that minimize the…

Low-light image enhancement (LLIE) is a crucial task in computer vision aimed at enhancing the visual fidelity of images captured under low-illumination conditions. Conventional methods frequently struggle with noise, overexposure, and…

Medical image segmentation remains challenging due to intensity inhomogeneity, noise, blurred boundaries, and irregular structures. Traditional level set methods, while effective in certain cases, often depend on approximate bias field…

Image structure-texture decomposition is a long-standing and fundamental problem in both image processing and computer vision fields. In this paper, we propose a generalized semi-sparse regularization framework for image structural analysis…

Previous literature suggests that perceptual similarity is an emergent property shared across deep visual representations. Experiments conducted on a dataset of human-judged image distortions have proven that deep features outperform…

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…

This paper addresses the problem of inverse rendering from photometric images. Existing approaches for this problem suffer from the effects of self-shadows, inter-reflections, and lack of constraints on the surface reflectance, leading to…

Recently, DETR pioneered the solution of vision tasks with transformers, it directly translates the image feature map into the object detection result. Though effective, translating the full feature map can be costly due to redundant…

Eliminating reflections caused by incident light interacting with reflective medium remains an ill-posed problem in the image restoration area. The primary challenge arises from the overlapping of reflection and transmission components in…

We develop a linear algebraic framework for the shape-from-shading problem, because tensors arise when scalar (e.g. image) and vector (e.g. surface normal) fields are differentiated multiple times. Using this framework, we first investigate…

Density reconstruction from X-ray projections is an important problem in radiography with key applications in scientific and industrial X-ray computed tomography (CT). Often, such projections are corrupted by unknown sources of noise and…

Recent advances in diffusion-based Large Restoration Models (LRMs) have significantly improved photo-realistic image restoration by leveraging the internal knowledge embedded within model weights. However, existing LRMs often suffer from…