Related papers: Learning Generative Structure Prior for Blind Text…

A promise of Generative Adversarial Networks (GANs) is to provide cheap photorealistic data for training and validating AI models in autonomous driving. Despite their huge success, their performance on complex images featuring multiple…

Recently, significant advancements have been made in diffusion-based visual text generation models. Although the effectiveness of these methods in visual text rendering is rapidly improving, they still encounter challenges such as…

Convolutional Neural Networks (CNNs) have significantly advanced Image Super-Resolution (SR), yet most CNN-based methods rely solely on pixel-based transformations, often leading to artifacts and blurring, particularly under severe…

Typical methods for text-to-image synthesis seek to design effective generative architecture to model the text-to-image mapping directly. It is fairly arduous due to the cross-modality translation. In this paper we circumvent this problem…

In text recognition, complex glyphs and tail classes have always been factors affecting model performance. Specifically for Chinese text recognition, the lack of shape-awareness can lead to confusion among close complex characters. Since…

We propose to improve text recognition from a new perspective by separating the text content from complex backgrounds. As vanilla GANs are not sufficiently robust to generate sequence-like characters in natural images, we propose an…

Generating an image from a provided descriptive text is quite a challenging task because of the difficulty in incorporating perceptual information (object shapes, colors, and their interactions) along with providing high relevancy related…

The Super-Resolution Generative Adversarial Network (SRGAN) is a seminal work that is capable of generating realistic textures during single image super-resolution. However, the hallucinated details are often accompanied with unpleasant…

Synthetic image generation has recently experienced significant improvements in domains such as natural image or art generation. However, the problem of figure and diagram generation remains unexplored. A challenging aspect of generating…

Generating desired images conditioned on given text descriptions has received lots of attention. Recently, diffusion models and autoregressive models have demonstrated their outstanding expressivity and gradually replaced GAN as the favored…

Deep generative models like StyleGAN hold the promise of semantic image editing: modifying images by their content, rather than their pixel values. Unfortunately, working with arbitrary images requires inverting the StyleGAN generator,…

Generative Adversarial Networks (GANs) are powerful tools for reconstructing Compressed Sensing Magnetic Resonance Imaging (CS-MRI). However most recent works lack exploration of structure information of MRI images that is crucial for…

Existing face restoration researches typically relies on either the degradation prior or explicit guidance labels for training, which often results in limited generalization ability over real-world images with heterogeneous degradations and…

Most super-resolution (SR) models struggle with real-world low-resolution (LR) images. This issue arises because the degradation characteristics in the synthetic datasets differ from those in real-world LR images. Since SR models are…

Recent generative-prior-based methods have shown promising blind face restoration performance. They usually project the degraded images to the latent space and then decode high-quality faces either by single-stage latent optimization or…

Character line drawing synthesis can be formulated as a special case of image-to-image translation problem that automatically manipulates the photo-to-line drawing style transformation. In this paper, we present the first generative…

Single image super-resolution (SR) via deep learning has recently gained significant attention in the literature. Convolutional neural networks (CNNs) are typically learned to represent the mapping between low-resolution (LR) and…

Single image super resolution (SR), which refers to reconstruct a higher-resolution (HR) image from the observed low-resolution (LR) image, has received substantial attention due to its tremendous application potentials. Despite the…

The research topic of sketch-to-portrait generation has witnessed a boost of progress with deep learning techniques. The recently proposed StyleGAN architectures achieve state-of-the-art generation ability but the original StyleGAN is not…

Recent face generation methods have tried to synthesize faces based on the given contour condition, like a low-resolution image or sketch. However, the problem of identity ambiguity remains unsolved, which usually occurs when the contour is…