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

Feature representations, both hand-designed and learned ones, are often hard to analyze and interpret, even when they are extracted from visual data. We propose a new approach to study image representations by inverting them with an…

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…

Numerous image superresolution (SR) algorithms have been proposed for reconstructing high-resolution (HR) images from input images with lower spatial resolutions. However, effectively evaluating the perceptual quality of SR images remains a…

We present SfSNet, an end-to-end learning framework for producing an accurate decomposition of an unconstrained human face image into shape, reflectance and illuminance. SfSNet is designed to reflect a physical lambertian rendering model.…

In this paper we develop FaceQgen, a No-Reference Quality Assessment approach for face images based on a Generative Adversarial Network that generates a scalar quality measure related with the face recognition accuracy. FaceQgen does not…

Cross-resolution face recognition has become a challenging problem for modern deep face recognition systems. It aims at matching a low-resolution probe image with high-resolution gallery images registered in a database. Existing methods…

How to generate the ground-truth (GT) image is a critical issue for training realistic image super-resolution (Real-ISR) models. Existing methods mostly take a set of high-resolution (HR) images as GTs and apply various degradations to…

To improve the performance of blind face restoration, recent works mainly treat the two aspects, i.e., generic and specific restoration, separately. In particular, generic restoration attempts to restore the results through general facial…

Image super-resolution (SR) has been widely investigated in recent years. However, it is challenging to fairly estimate the performance of various SR methods, as the lack of reliable and accurate criteria for the perceptual quality.…

Learning-based image harmonization techniques are usually trained to undo synthetic random global transformations applied to a masked foreground in a single ground truth photo. This simulated data does not model many of the important…

Existing face relighting methods often struggle with two problems: maintaining the local facial details of the subject and accurately removing and synthesizing shadows in the relit image, especially hard shadows. We propose a novel deep…

The capabilities of super-resolution reconstruction (SRR)---techniques for enhancing image spatial resolution---have been recently improved significantly by the use of deep convolutional neural networks. Commonly, such networks are learned…

Face super-resolution methods usually aim at producing visually appealing results rather than preserving distinctive features for further face identification. In this work, we propose a deep learning method for face verification on very…

The aim of image restoration is to recover high-quality images from distorted ones. However, current methods usually focus on a single task (\emph{e.g.}, denoising, deblurring or super-resolution) which cannot address the needs of…

The difficulty of obtaining paired data remains a major bottleneck for learning image restoration and enhancement models for real-world applications. Current strategies aim to synthesize realistic training data by modeling noise and…

Despite that convolutional neural networks (CNN) have recently demonstrated high-quality reconstruction for single-image super-resolution (SR), recovering natural and realistic texture remains a challenging problem. In this paper, we show…

Generic Face Image Quality Assessment (GFIQA) evaluates the perceptual quality of facial images, which is crucial in improving image restoration algorithms and selecting high-quality face images for downstream tasks. We present a novel…

Numerous style transfer methods which produce artistic styles of portraits have been proposed to date. However, the inverse problem of converting the stylized portraits back into realistic faces is yet to be investigated thoroughly.…

Deep learning-based image restoration has achieved significant success. However, when addressing real-world degradations, model performance is limited by the quality of groundtruth images in datasets due to practical constraints in data…

In the real world, the degradation of images taken under haze can be quite complex, where the spatial distribution of haze is varied from image to image. Recent methods adopt deep neural networks to recover clean scenes from hazy images…