Related papers: PGP-DiffSR: Phase-Guided Progressive Pruning for E…

We propose Diff-Shadow, a global-guided diffusion model for shadow removal. Previous transformer-based approaches can utilize global information to relate shadow and non-shadow regions but are limited in their synthesis ability and recover…

Diffusion-based image super-resolution (SR) methods have achieved remarkable success by leveraging large pre-trained text-to-image diffusion models as priors. However, these methods still face two challenges: the requirement for dozens of…

Image restoration is a classic low-level problem aimed at recovering high-quality images from low-quality images with various degradations such as blur, noise, rain, haze, etc. However, due to the inherent complexity and non-uniqueness of…

Diffusion-based super-resolution (SR) models have recently garnered significant attention due to their potent restoration capabilities. But conventional diffusion models perform noise sampling from a single distribution, constraining their…

Despite the remarkable generation capabilities of Diffusion Models (DMs), conducting training and inference remains computationally expensive. Previous works have been devoted to accelerating diffusion sampling, but achieving data-efficient…

Decompositional reconstruction of 3D scenes, with complete shapes and detailed texture of all objects within, is intriguing for downstream applications but remains challenging, particularly with sparse views as input. Recent approaches…

In this paper, we propose GuideSR, a novel single-step diffusion-based image super-resolution (SR) model specifically designed to enhance image fidelity. Existing diffusion-based SR approaches typically adapt pre-trained generative models…

Diffusion models have achieved remarkable progress in universal image restoration. While existing methods speed up inference by reducing sampling steps, substantial step intervals often introduce cumulative errors. Moreover, they struggle…

Recently, convolutional networks have achieved remarkable development in remote sensing image Super-Resoltuion (SR) by minimizing the regression objectives, e.g., MSE loss. However, despite achieving impressive performance, these methods…

While diffusion-based image restoration (IR) methods have achieved remarkable success, they are still limited by the low inference speed attributed to the necessity of executing hundreds or even thousands of sampling steps. Existing…

Benefiting from their powerful generative capabilities, pretrained diffusion models have garnered significant attention for real-world image super-resolution (Real-SR). Existing diffusion-based SR approaches typically utilize semantic…

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…

While diffusion models significantly improve the perceptual quality of super-resolved images, they usually require a large number of sampling steps, resulting in high computational costs and long inference times. Recent efforts have…

Diffusion-based models have achieved notable empirical successes in reinforcement learning (RL) due to their expressiveness in modeling complex distributions. Despite existing methods being promising, the key challenge of extending existing…

Diffusion models have demonstrated impressive image synthesis performance, yet many UNet-based models are trained at certain fixed resolutions. Their quality tends to degrade when generating images at out-of-training resolutions. We trace…

Generative diffusion models, famous for their performance in image generation, are popular in various cross-domain applications. However, their use in the communication community has been mostly limited to auxiliary tasks like data modeling…

While burst LR images are useful for improving the SR image quality compared with a single LR image, prior SR networks accepting the burst LR images are trained in a deterministic manner, which is known to produce a blurry SR image. In…

Diffusion models have shown remarkable flexibility for solving inverse problems without task-specific retraining. However, existing approaches such as Manifold Preserving Guided Diffusion (MPGD) apply only a single gradient update per…

The generative priors of pre-trained latent diffusion models (DMs) have demonstrated great potential to enhance the visual quality of image super-resolution (SR) results. However, the noise sampling process in DMs introduces randomness in…

Existing single image reflection removal (SIRR) methods using deep learning tend to miss key low-frequency (LF) and high-frequency (HF) differences in images, affecting their effectiveness in removing reflections. To address this problem,…