Related papers: ShadingNet: Image Intrinsics by Fine-Grained Shadi…
Image harmonization aims to adjust the foreground illumination in a composite image to make it harmonious. The existing harmonization methods can only produce one deterministic result for a composite image, ignoring that a composite image…
We cast shape matching as metric learning with convolutional networks. We break the end-to-end process of image representation into two parts. Firstly, well established efficient methods are chosen to turn the images into edge maps.…
Deformable image registration is a fundamental task in medical image analysis, aiming to establish a dense and non-linear correspondence between a pair of images. Previous deep-learning studies usually employ supervised neural networks to…
Recent learning-based lossless image compression methods encode an image in the unit of subimages and achieve comparable performances to conventional non-learning algorithms. However, these methods do not consider the performance drop in…
Accurate intrinsic decomposition of face images under unconstrained lighting is a prerequisite for photorealistic relighting, high-fidelity digital doubles, and augmented-reality effects. This paper introduces MAGINet, a Multi-scale…
Empowered by deep learning, recent methods for material capture can estimate a spatially-varying reflectance from a single photograph. Such lightweight capture is in stark contrast with the tens or hundreds of pictures required by…
Deep convolutional neural networks perform better on images containing spatially invariant noise (synthetic noise); however, their performance is limited on real-noisy photographs and requires multiple stage network modeling. To advance the…
We present Intrinsic Image Diffusion, a generative model for appearance decomposition of indoor scenes. Given a single input view, we sample multiple possible material explanations represented as albedo, roughness, and metallic maps.…
Single-view intrinsic image decomposition is a highly ill-posed problem, and so a promising approach is to learn from large amounts of data. However, it is difficult to collect ground truth training data at scale for intrinsic images. In…
We propose to learn a fully-convolutional network model that consists of a Chain of Identity Mapping Modules and residual on the residual architecture for image denoising. Our network structure possesses three distinctive features that are…
Few-shot fine-grained image classification aims to recognize subcategories with high visual similarity using only a limited number of annotated samples. Existing metric learning-based methods typically rely solely on spatial domain…
Texture, highlights, and shading are some of many visual cues that allow humans to perceive material appearance in single pictures. Yet, recovering spatially-varying bi-directional reflectance distribution functions (SVBRDFs) from a single…
The non-uniform photoelectric response of infrared imaging systems results in fixed-pattern stripe noise being superimposed on infrared images, which severely reduces image quality. As the applications of degraded infrared images are…
Deep neural networks (DNN) have achieved great success in image restoration. However, most DNN methods are designed as a black box, lacking transparency and interpretability. Although some methods are proposed to combine traditional…
Single image dehazing is a challenging ill-posed restoration problem. Various prior-based and learning-based methods have been proposed. Most of them follow a classic atmospheric scattering model which is an elegant simplified physical…
We show how to insert an object from one image to another and get realistic results in the hard case, where the shading of the inserted object clashes with the shading of the scene. Rendering objects using an illumination model of the scene…
Image dehazing is an important task in the field of computer vision, aiming at restoring clear and detail-rich visual content from haze-affected images. However, when dealing with complex scenes, existing methods often struggle to strike a…
Previous face inverse rendering methods often require synthetic data with ground truth and/or professional equipment like a lighting stage. However, a model trained on synthetic data or using pre-defined lighting priors is typically unable…
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…
Despite significant progress in shadow detection, current methods still struggle with the adverse impact of background color, which may lead to errors when shadows are present on complex backgrounds. Drawing inspiration from the human…