Related papers: BlindDiff: Empowering Degradation Modelling in Dif…
With sufficient paired training samples, the supervised deep learning methods have attracted much attention in image denoising because of their superior performance. However, it is still very challenging to widely utilize the supervised…
Multiple Instance Learning (MIL), a powerful strategy for weakly supervised learning, is able to perform various prediction tasks on gigapixel Whole Slide Images (WSIs). However, the tens of thousands of patches in WSIs usually incur a vast…
Existing image restoration methods mostly leverage the posterior distribution of natural images. However, they often assume known degradation and also require supervised training, which restricts their adaptation to complex real…
Blind Super-Resolution (blind SR) aims to enhance the model's generalization ability with unknown degradation, yet it still encounters severe overfitting issues. Some previous methods inspired by dropout, which enhances generalization by…
Detail features of magnetic resonance images play a cru-cial role in accurate medical diagnosis and treatment, as they capture subtle changes that pose challenges for doc-tors when performing precise judgments. However, the widely utilized…
Deep MRI reconstruction is commonly performed with conditional models that de-alias undersampled acquisitions to recover images consistent with fully-sampled data. Since conditional models are trained with knowledge of the imaging operator,…
This study investigates the application of deep-learning diffusion models for the super-resolution of weather data, a novel approach aimed at enhancing the spatial resolution and detail of meteorological variables. Leveraging the…
Low-dose Positron Emission Tomography (PET) reduces radiation exposure but suffers from severe noise and quantitative degradation. Diffusion-based denoising models achieve strong final reconstructions, yet their reverse trajectories are…
This paper introduces innovative solutions to enhance spatial controllability in diffusion models reliant on text queries. We first introduce vision guidance as a foundational spatial cue within the perturbed distribution. This…
Deep neural networks have recently achieved significant advancements in remote sensing superresolu-tion (SR). However, most existing methods are limited to low magnification rates (e.g., 2 or 4) due to the escalating ill-posedness at higher…
Real-world image super-resolution is particularly challenging for diffusion models because real degradations are complex, heterogeneous, and rarely modeled explicitly. We propose a degradation-aware and structure-preserving diffusion…
Recent efforts have witnessed remarkable progress in Satellite Video Super-Resolution (SVSR). However, most SVSR methods usually assume the degradation is fixed and known, e.g., bicubic downsampling, which makes them vulnerable in…
Diffusion models (DMs) have emerged as powerful generative models for solving inverse problems, offering a good approximation of prior distributions of real-world image data. Typically, diffusion models rely on large-scale clean signals to…
Existing fusion methods are tailored for high-quality images but struggle with degraded images captured under harsh circumstances, thus limiting the practical potential of image fusion. This work presents a \textbf{D}egradation and…
Recent state-of-the-art image restoration methods mostly adopt latent diffusion models with U-Net backbones, yet still facing challenges in achieving high-quality restoration due to their limited capabilities. Diffusion transformers (DiTs),…
While supervised stereo matching and monocular depth estimation have advanced significantly with learning-based algorithms, self-supervised methods using stereo images as supervision signals have received relatively less focus and require…
In this work, we utilize the high-fidelity generation abilities of diffusion models to solve blind JPEG restoration at high compression levels. We propose an elegant modification of the forward stochastic differential equation of diffusion…
Forward scatter radar (FSR) has emerged as an effective imaging modality for target detection, utilizing forward scattering (FS) signals to reconstruct two-dimensional shadow profile images of objects. However, real-world FS signals are…
Diffusion models (DMs), lauded for their generative performance, are computationally prohibitive due to their billion-scale parameters and iterative denoising dynamics. Existing efficiency techniques, such as quantization, timestep…
Deep learning-based image compression algorithms typically focus on designing encoding and decoding networks and improving the accuracy of entropy model estimation to enhance the rate-distortion (RD) performance. However, few algorithms…