Related papers: MGHF: Multi-Granular High-Frequency Perceptual Los…
Perceptual image restoration seeks for high-fidelity images that most likely degrade to given images. For better visual quality, previous work proposed to search for solutions within the natural image manifold, by exploiting the latent…
Currently, there are two popular approaches for addressing real-world image super-resolution problems: degradation-estimation-based and blind-based methods. However, degradation-estimation-based methods may be inaccurate in estimating the…
Image rescaling is a commonly used bidirectional operation, which first downscales high-resolution images to fit various display screens or to be storage- and bandwidth-friendly, and afterward upscales the corresponding low-resolution…
The perceptual loss has been widely used as an effective loss term in image synthesis tasks including image super-resolution, and style transfer. It was believed that the success lies in the high-level perceptual feature representations…
Pansharpening is a widely used image enhancement technique for remote sensing. Its principle is to fuse the input high-resolution single-channel panchromatic (PAN) image and low-resolution multi-spectral image and to obtain a…
By converting low-frame-rate, low-resolution videos into high-frame-rate, high-resolution ones, space-time video super-resolution techniques can enhance visual experiences and facilitate more efficient information dissemination. We propose…
Although image restoration has advanced significantly, most existing methods target only a single type of degradation. In real-world scenarios, images often contain multiple degradations simultaneously, such as rain, noise, and haze,…
Existing frameworks for image stitching often provide visually reasonable stitchings. However, they suffer from blurry artifacts and disparities in illumination, depth level, etc. Although the recent learning-based stitchings relax such…
Image inpainting seeks a semantically consistent way to recover the corrupted image in the light of its unmasked content. Previous approaches usually reuse the well-trained GAN as effective prior to generate realistic patches for missing…
Image denoising is a fundamental and challenging task in the field of computer vision. Most supervised denoising methods learn to reconstruct clean images from noisy inputs, which have intrinsic spectral bias and tend to produce…
The integral image, an intermediate image representation, has found extensive use in multi-scale local feature detection algorithms, such as Speeded-Up Robust Features (SURF), allowing fast computation of rectangular features at constant…
Implicit Neural Representations (INRs) have garnered significant attention for their ability to model complex signals in various domains. Recently, INR-based frameworks have shown promise in neural video compression by embedding video…
Image-text retrieval is a central problem for understanding the semantic relationship between vision and language, and serves as the basis for various visual and language tasks. Most previous works either simply learn coarse-grained…
For multi-scale problems, the conventional physics-informed neural networks (PINNs) face some challenges in obtaining available predictions. In this paper, based on PINNs, we propose a practical deep learning framework for multi-scale…
The purpose of image inpainting is to recover scratches and damaged areas using context information from remaining parts. In recent years, thanks to the resurgence of convolutional neural networks (CNNs), image inpainting task has made…
Computer-generated holography (CGH) enables applications in holographic augmented reality (AR), 3D displays, systems neuroscience, and optical trapping. The fundamental challenge in CGH is solving the inverse problem of phase retrieval from…
Magnetic resonance imaging plays an important role in computer-aided diagnosis and brain exploration. However, limited by hardware, scanning time and cost, it's challenging to acquire high-resolution (HR) magnetic resonance (MR) image…
Intrinsic decomposition from a single image is a highly challenging task, due to its inherent ambiguity and the scarcity of training data. In contrast to traditional fully supervised learning approaches, in this paper we propose learning…
Recently, Transformer-based methods have shown impressive performance in single image super-resolution (SISR) tasks due to the ability of global feature extraction. However, the capabilities of Transformers that need to incorporate…
Recently, it has been demonstrated that deep neural networks can significantly improve the performance of single image super-resolution (SISR). Numerous studies have concentrated on raising the quantitative quality of super-resolved (SR)…