相关论文: Removing Reflections from RAW Photos

A simple, yet general, formalism for the optimized linear combination of astrophysical images is constructed and demonstrated. The formalism allows the user to combine multiple undersampled images to provide oversampled output at high…

A technique is presented for producing synthetic images from numerical simulations whereby the image resolution is adapted around prominent features. In so doing, adaptive image ray-tracing (AIR) improves the efficiency of a calculation by…

Using RAW-images in computer vision problems is surprisingly underexplored considering that converting from RAW to RGB does not introduce any new capture information. In this paper, we show that a sufficiently advanced classifier can yield…

Flatbed scanners have emerged as promising devices for high-resolution, single-image material capture. However, existing approaches assume very specific conditions, such as uniform diffuse illumination, which are only available in certain…

Inverse rendering of an object under entirely unknown capture conditions is a fundamental challenge in computer vision and graphics. Neural approaches such as NeRF have achieved photorealistic results on novel view synthesis, but they…

Acquired images for medical and other purposes can be affected by noise from both the equipment used in the capturing or the environment. This can have adverse effect on the information therein. Thus, the need to restore the image to its…

Automatic document content processing is affected by artifacts caused by the shape of the paper, non-uniform and diverse color of lighting conditions. Fully-supervised methods on real data are impossible due to the large amount of data…

Most image deblurring methods assume an over-simplistic image formation model and as a result are sensitive to more realistic image degradations. We propose a novel variational framework, that explicitly handles pixel saturation, noise,…

Most of the existing learning-based single image superresolution (SISR) methods are trained and evaluated on simulated datasets, where the low-resolution (LR) images are generated by applying a simple and uniform degradation (i.e., bicubic…

Photographs taken through a glass surface often contain an approximately linear superposition of reflected and transmitted layers. Decomposing an image into these layers is generally an ill-posed task and the use of an additional image…

Capturing and labeling camera images in the real world is an expensive task, whereas synthesizing labeled images in a simulation environment is easy for collecting large-scale image data. However, learning from only synthetic images may not…

Real-world deployment of AI vision models is both fueled and limited by the data available for training and testing. Real datasets are sparse and uneven: long-tailed or unbalanced distributions hinder generalization, and the low number of…

We present the RAW domain diffusion model (RDDM), an end-to-end diffusion model that restores photo-realistic images directly from the sensor RAW data. While recent sRGB-domain diffusion methods achieve impressive results, they are caught…

Wide field-of-view (FOV) cameras, which capture a larger scene area than narrow FOV cameras, are used in many applications including 3D reconstruction, autonomous driving, and video surveillance. However, wide-angle images contain…

Traditionally, the main focus of image super-resolution techniques is on recovering the most likely high-quality images from low-quality images, using a one-to-one low- to high-resolution mapping. Proceeding that way, we ignore the fact…

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…

Inverse rendering methods aim to estimate geometry, materials and illumination from multi-view RGB images. In order to achieve better decomposition, recent approaches attempt to model indirect illuminations reflected from different…

Unprocessed RAW data is a highly valuable image format for image editing and computer vision. However, since the file size of RAW data is huge, most users can only get access to processed and compressed sRGB images. To bridge this gap, we…

Machine learning techniques work best when the data used for training resembles the data used for evaluation. This holds true for learned single-image denoising algorithms, which are applied to real raw camera sensor readings but, due to…

Although recent learning-based calibration methods can predict extrinsic and intrinsic camera parameters from a single image, the accuracy of these methods is degraded in fisheye images. This degradation is caused by mismatching between the…