Related papers: SSP-IR: Semantic and Structure Priors for Diffusio…
Recent deep learning methods have achieved promising results in image shadow removal. However, their restored images still suffer from unsatisfactory boundary artifacts, due to the lack of degradation prior embedding and the deficiency in…
Text-to-image diffusion models have emerged as powerful priors for real-world image super-resolution (Real-ISR). However, existing methods may produce unintended results due to noisy text prompts and their lack of spatial information. In…
Diffusion-based image super-resolution (SR) has recently attracted significant attention by leveraging the expressive power of large pre-trained text-to-image diffusion models (DMs). A central practical challenge is resolving the trade-off…
Phase retrieval aims to recover a signal from intensity-only measurements, a fundamental problem in many fields such as imaging, holography, optical computing, crystallography, and microscopy. Although there are several well-known phase…
Generative diffusion models (DM) have been extensively utilized in image super-resolution (ISR). Most of the existing methods adopt the denoising loss from DDPMs for model optimization. We posit that introducing reward feedback learning to…
Generalization has long been a central challenge in real-world image restoration. While recent diffusion-based restoration methods, which leverage generative priors from text-to-image models, have made progress in recovering more realistic…
Image restoration refers to the process of restoring a damaged low-quality image back to its corresponding high-quality image. Typically, we use convolutional neural networks to directly learn the mapping from low-quality images to…
Recovering High Dynamic Range (HDR) images from multiple Standard Dynamic Range (SDR) images become challenging when the SDR images exhibit noticeable degradation and missing content. Leveraging scene-specific semantic priors offers a…
Diffusion models (DMs) have recently been introduced in image deblurring and exhibited promising performance, particularly in terms of details reconstruction. However, the diffusion model requires a large number of inference iterations to…
Diffusion models (DMs) have exhibited remarkable efficacy in various image restoration tasks. However, existing approaches typically operate within the high-dimensional pixel space, resulting in high computational overhead. While methods…
Spectral computed tomography (CT) with photon-counting detectors holds immense potential for material discrimination and tissue characterization. However, under ultra-low-dose conditions, the sharply degraded signal-to-noise ratio (SNR) in…
Recent progress in generative models has significantly improved image restoration capabilities, particularly through powerful diffusion models that offer remarkable recovery of semantic details and local fidelity. However, deploying these…
Real-world noise removal is crucial in low-level computer vision. Due to the remarkable generation capabilities of diffusion models, recent attention has shifted towards leveraging diffusion priors for image restoration tasks. However,…
Perceptual image compression has shown strong potential for producing visually appealing results at low bitrates, surpassing classical standards and pixel-wise distortion-oriented neural methods. However, existing methods typically improve…
Diffusion Probabilistic Models (DPMs) have recently shown remarkable performance in image generation tasks, which are capable of generating highly realistic images. When adopting DPMs for image restoration tasks, the crucial aspect lies in…
Diffusion-based models have been widely used in various visual generation tasks, showing promising results in image super-resolution (SR), while typically being limited by dozens or even hundreds of sampling steps. Although existing methods…
Structures matter in single image super-resolution (SISR). Benefiting from generative adversarial networks (GANs), recent studies have promoted the development of SISR by recovering photo-realistic images. However, there are still undesired…
Most existing MRI reconstruction methods perform tar-geted reconstruction of the entire MR image without tak-ing specific tissue regions into consideration. This may fail to emphasize the reconstruction accuracy on im-portant tissues for…
Diffusion-based image super-resolution (SR) methods are mainly limited by the low inference speed due to the requirements of hundreds or even thousands of sampling steps. Existing acceleration sampling techniques inevitably sacrifice…
In dynamic scenes, images often suffer from dynamic blur due to superposition of motions or low signal-noise ratio resulted from quick shutter speed when avoiding motions. Recovering sharp and clean results from the captured images heavily…