相关论文: From Face to Natural Image: Learning Real Degradat…

Face Restoration (FR) aims to restore High-Quality (HQ) faces from Low-Quality (LQ) input images, which is a domain-specific image restoration problem in the low-level computer vision area. The early face restoration methods mainly use…

Super-resolution and denoising are ill-posed yet fundamental image restoration tasks. In blind settings, the degradation kernel or the noise level are unknown. This makes restoration even more challenging, notably for learning-based…

Intrinsic image decomposition is the process of separating the reflectance and shading layers of an image, which is a challenging and underdetermined problem. In this paper, we propose to systematically address this problem using a deep…

This paper studies the problem of blind face restoration from an unconstrained blurry, noisy, low-resolution, or compressed image (i.e., degraded observation). For better recovery of fine facial details, we modify the problem setting by…

Facial image super-resolution (SR) is an important preprocessing for facial image analysis, face recognition, and image-based 3D face reconstruction. Recent convolutional neural network (CNN) based method has shown excellent performance by…

High-resolution representations are essential for position-sensitive vision problems, such as human pose estimation, semantic segmentation, and object detection. Existing state-of-the-art frameworks first encode the input image as a…

We present a method to improve the visual realism of low-quality, synthetic images, e.g. OpenGL renderings. Training an unpaired synthetic-to-real translation network in image space is severely under-constrained and produces visible…

In real-world scenarios, due to a series of image degradations, obtaining high-quality, clear content photos is challenging. While significant progress has been made in synthesizing high-quality images, previous methods for image…

Image degradation synthesis is highly desirable in a wide variety of applications ranging from image restoration to simulating artistic effects. Existing models are designed to generate one specific or a narrow set of degradations, which…

The training of real-world super-resolution reconstruction models heavily relies on datasets that reflect real-world degradation patterns. Extracting and modeling degradation patterns for super-resolution reconstruction using only…

Most current super-resolution methods rely on low and high resolution image pairs to train a network in a fully supervised manner. However, such image pairs are not available in real-world applications. Instead of directly addressing this…

Traditional blind image SR methods need to model real-world degradations precisely. Consequently, current research struggles with this dilemma by assuming idealized degradations, which leads to limited applicability to actual user data.…

Most single image super-resolution (SR) methods are developed on synthetic low-resolution (LR) and high-resolution (HR) image pairs, which are simulated by a predetermined degradation operation, e.g., bicubic downsampling. However, these…

The performance of deep learning based image super-resolution (SR) methods depend on how accurately the paired low and high resolution images for training characterize the sampling process of real cameras. Low and high resolution…

Hand-held light field (LF) cameras often exhibit low spatial resolution due to the inherent trade-off between spatial and angular dimensions. Existing supervised learning-based LF spatial super-resolution (SR) methods, which rely on…

Automatic Perceptual Image Quality Assessment is a challenging problem that impacts billions of internet, and social media users daily. To advance research in this field, we propose a Mixture of Experts approach to train two separate…

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…

Existing image super-resolution (SR) techniques often fail to generalize effectively in complex real-world settings due to the significant divergence between training data and practical scenarios. To address this challenge, previous efforts…

Single image super resolution aims to enhance image quality with respect to spatial content, which is a fundamental task in computer vision. In this work, we address the task of single frame super resolution with the presence of image…

Current methods for single-image depth estimation use training datasets with real image-depth pairs or stereo pairs, which are not easy to acquire. We propose a framework, trained on synthetic image-depth pairs and unpaired real images,…