Related papers: Physics-consistent deep learning for blind aberrat…
Mobile cameras, despite their significant advancements, still have difficulty in low-light imaging due to compact sensors and lenses, leading to longer exposures and motion blur. Traditional blind deconvolution methods and learning-based…
Removing camera motion blur from a single light field is a challenging task since it is highly ill-posed inverse problem. The problem becomes even worse when blur kernel varies spatially due to scene depth variation and high-order camera…
Deblurring is the task of restoring a blurred image to a sharp one, retrieving the information lost due to the blur. In blind deblurring we have no information regarding the blur kernel. As deblurring can be considered as an image to image…
We consider the problem of high-dimensional light field reconstruction and develop a learning-based framework for spatial and angular super-resolution. Many current approaches either require disparity clues or restore the spatial and…
Deep learning has demonstrated superb efficacy in processing imaging data, yet its suitability in solving challenging inverse problems in scientific imaging has not been fully explored. Of immense interest is the determination of local…
We address for the first time the issue of motion blur in light field images captured from plenoptic cameras. We propose a solution to the estimation of a sharp high resolution scene radiance given a blurry light field image, when the…
This work presents a new unsupervised framework for training deep learning models for super-resolution of Sentinel-2 images by fusion of its 10-m and 20-m bands. The proposed scheme avoids the resolution downgrade process needed to generate…
Vision-language models (VLMs) frequently generate hallucinated content plausible but incorrect claims about image content. We propose a training-free self-correction framework enabling VLMs to iteratively refine responses through…
Deep neural network based methods are the state of the art in various image restoration problems. Standard supervised learning frameworks require a set of noisy measurement and clean image pairs for which a distance between the output of…
Image degradation caused by noise and blur remains a persistent challenge in imaging systems, stemming from limitations in both hardware and methodology. Single-image solutions face an inherent tradeoff between noise reduction and motion…
Scanning microscopy systems, such as confocal and multiphoton microscopy, are powerful imaging tools for probing deep into biological tissue. However, scanning systems have an inherent trade-off between acquisition time, field of view,…
We propose a very fast and effective one-step restoring method for blurry face images. In the last decades, many blind deblurring algorithms have been proposed to restore latent sharp images. However, these algorithms run slowly because of…
By adopting popular pixel-wise loss, existing methods for defocus deblurring heavily rely on well aligned training image pairs. Although training pairs of ground-truth and blurry images are carefully collected, e.g., DPDD dataset,…
Fourier ptychography (FP) is a newly developed computational imaging approach that achieves both high resolution and wide field of view by stitching a series of low-resolution images captured under angle-varied illumination. So far, many…
We propose and implement an aberration correction method for the creation of extended arrays of spots well beyond the isoplanatic region of any optical system. The method relies on an extensive calibration of aberrations in terms of Zernike…
Color-coded aperture (CCA) methods can physically measure the depth of a scene given by physical cues from a single-shot image of a monocular camera. However, they are vulnerable to actual lens aberrations in real scenes because they assume…
Recognizing symmetries in data allows for significant boosts in neural network training, which is especially important where training data are limited. In many cases, however, the exact underlying symmetry is present only in an idealized…
We present a new deep supervised learning method for intrinsic decomposition of a single image into its albedo and shading components. Our contributions are based on a new fully convolutional neural network that estimates absolute albedo…
Inverse rendering is the problem of decomposing an image into its intrinsic components, i.e. albedo, normal and lighting. To solve this ill-posed problem from single image, state-of-the-art methods in shape from shading mostly resort to…
This work presents a probabilistic deep neural network that combines LiDAR point clouds and RGB camera images for robust, accurate 3D object detection. We explicitly model uncertainties in the classification and regression tasks, and…