Related papers: Enforcing Perceptual Consistency on Generative Adv…

Generative Adversarial Networks (GAN) have demonstrated the potential to recover realistic details for single image super-resolution (SISR). To further improve the visual quality of super-resolved results, PIRM2018-SR Challenge employed…

In recent years, deep neural networks have been utilized in a wide variety of applications including image generation. In particular, generative adversarial networks (GANs) are able to produce highly realistic pictures as part of tasks such…

In this paper, we propose a novel normalization method called penalty gradient normalization (PGN) to tackle the training instability of Generative Adversarial Networks (GANs) caused by the sharp gradient space. Unlike existing work such as…

Multi-domain image-to-image translation with conditional Generative Adversarial Networks (GANs) can generate highly photo realistic images with desired target classes, yet these synthetic images have not always been helpful to improve…

Generative Adversarial Networks (GAN) is currently widely used as an unsupervised image generation method. Current state-of-the-art GANs can generate photorealistic images with high resolution. However, a large amount of data is required,…

Image-based generative methods, such as generative adversarial networks (GANs) have already been able to generate realistic images with much context control, specially when they are conditioned. However, most successful frameworks share a…

In this paper, we propose a novel regularization method for Generative Adversarial Networks, which allows the model to learn discriminative yet compact binary representations of image patches (image descriptors). We employ the…

Classifiers and generators have long been separated. We break down this separation and showcase that conventional neural network classifiers can generate high-quality images of a large number of categories, being comparable to the…

Features obtained from object recognition CNNs have been widely used for measuring perceptual similarities between images. Such differentiable metrics can be used as perceptual learning losses to train image enhancement models. However, the…

Deep learning models are found to be vulnerable to adversarial examples, as wrong predictions can be caused by small perturbation in input for deep learning models. Most of the existing works of adversarial image generation try to achieve…

Despite their recent successes, GAN models for semantic image synthesis still suffer from poor image quality when trained with only adversarial supervision. Historically, additionally employing the VGG-based perceptual loss has helped to…

Recently image inpainting has witnessed rapid progress due to generative adversarial networks (GAN) that are able to synthesize realistic contents. However, most existing GAN-based methods for semantic inpainting apply an auto-encoder…

Despite the recent success of stereo matching with convolutional neural networks (CNNs), it remains arduous to generalize a pre-trained deep stereo model to a novel domain. A major difficulty is to collect accurate ground-truth disparities…

The effects of adversarial training on semantic segmentation networks has not been thoroughly explored. While previous work has shown that adversarially-trained image classifiers can be used to perform image synthesis, we have yet to…

Similarity metrics have played a significant role in computer vision to capture the underlying semantics of images. In recent years, advanced similarity metrics, such as the Learned Perceptual Image Patch Similarity (LPIPS), have emerged.…

Generative Adversarial Networks (GANs) have facilitated a new direction to tackle the image-to-image transformation problem. Different GANs use generator and discriminator networks with different losses in the objective function. Still…

A good Text-to-Image model should not only generate high quality images, but also ensure the consistency between the text and the generated image. Previous models failed to simultaneously fix both sides well. This paper proposes a Gradual…

We propose NormalGAN, a fast adversarial learning-based method to reconstruct the complete and detailed 3D human from a single RGB-D image. Given a single front-view RGB-D image, NormalGAN performs two steps: front-view RGB-D rectification…

Generating realistic palmprint (more generally biometric) images has always been an interesting and, at the same time, challenging problem. Classical statistical models fail to generate realistic-looking palmprint images, as they are not…

Improving the aesthetic quality of images is challenging and eager for the public. To address this problem, most existing algorithms are based on supervised learning methods to learn an automatic photo enhancer for paired data, which…