Related papers: Learned holographic light transport
Interest point descriptors have fueled progress on almost every problem in computer vision. Recent advances in deep neural networks have enabled task-specific learned descriptors that outperform hand-crafted descriptors on many problems. We…
Image hazing aims to render a hazy image from a given clean one, which could be applied to a variety of practical applications such as gaming, filming, photographic filtering, and image dehazing. To generate plausible haze, we study two…
Inspired by the recently remarkable successes of Sparse Representation (SR), Collaborative Representation (CR) and sparse graph, we present a novel hypergraph model named Regression-based Hypergraph (RH) which utilizes the regression models…
High dynamic range (HDR) imaging is an important task in image processing that aims to generate well-exposed images in scenes with varying illumination. Although existing multi-exposure fusion methods have achieved impressive results,…
Hyperspectral imaging can help better understand the characteristics of different materials, compared with traditional image systems. However, only high-resolution multispectral (HrMS) and low-resolution hyperspectral (LrHS) images can…
Images acquired by computer vision systems under low light conditions have multiple characteristics like high noise, lousy illumination, reflectance, and bad contrast, which make object detection tasks difficult. Much work has been done to…
Recently deep learning-based methods have been applied in image compression and achieved many promising results. In this paper, we propose an improved hybrid layered image compression framework by combining deep learning and the traditional…
We apply convolutional neural networks (CNN) to the problem of image orientation detection in the context of determining the correct orientation (from 0, 90, 180, and 270 degrees) of a consumer photo. The problem is especially important for…
High-resolution representations are important for vision-based robotic grasping problems. Existing works generally encode the input images into low-resolution representations via sub-networks and then recover high-resolution…
Learning with neural networks from a continuous stream of visual information presents several challenges due to the non-i.i.d. nature of the data. However, it also offers novel opportunities to develop representations that are consistent…
Image representations, from SIFT and Bag of Visual Words to Convolutional Neural Networks (CNNs), are a crucial component of almost any image understanding system. Nevertheless, our understanding of them remains limited. In this paper we…
Real-time rendering with global illumination is crucial to afford the user realistic experience in virtual environments. We present a learning-based estimator to predict diffuse indirect illumination in screen space, which then is combined…
Since holography yields exact results, even in situations where perturbation theory is not applicable, it is an ideal framework for modeling strongly correlated systems. We extend previous holographic methods to take the dynamical charge…
This paper presents a comprehensive survey of computational imaging (CI) techniques and their transformative impact on computer vision (CV) applications. Conventional imaging methods often fail to deliver high-fidelity visual data in…
Color encoding of depth is shown to occur naturally in images of objects observed through diffraction gratings under common white light illumination. A synthetic image is then obtained from a single point of view, a phenomenon that can be…
We present a novel method for communicating between a camera and display by embedding and recovering hidden and dynamic information within a displayed image. A handheld camera pointed at the display can receive not only the display image,…
Experimental protocols at synchrotron light sources typically process and validate data only after an experiment has completed, which can lead to undetected errors and cannot enable online steering. Real-time data analysis can enable both…
Modern cameras have limited dynamic ranges and often produce images with saturated or dark regions using a single exposure. Although the problem could be addressed by taking multiple images with different exposures, exposure fusion methods…
We recover a video of the motion taking place in a hidden scene by observing changes in indirect illumination in a nearby uncalibrated visible region. We solve this problem by factoring the observed video into a matrix product between the…
Models for image representation learning are typically designed for either recognition or generation. Various forms of contrastive learning help models learn to convert images to embeddings that are useful for classification, detection, and…