Related papers: AutoDIR: Automatic All-in-One Image Restoration wi…

Image restoration tasks like deblurring, denoising, and dehazing usually need distinct models for each degradation type, restricting their generalization in real-world scenarios with mixed or unknown degradations. In this work, we propose…

Recent advances in generative image restoration (IR) have demonstrated impressive results. However, these methods are hindered by their substantial size and computational demands, rendering them unsuitable for deployment on edge devices.…

Existing All-in-One image restoration methods often fail to perceive degradation types and severity levels simultaneously, overlooking the importance of fine-grained quality perception. Moreover, these methods often utilize highly…

In this paper, we propose the first diffusion-based all-in-one video restoration method that utilizes the power of a pre-trained Stable Diffusion and a fine-tuned ControlNet. Our method can restore various types of video degradation with a…

Images captured in challenging environments often experience various forms of degradation, including noise, color cast, blur, and light scattering. These effects significantly reduce image quality, hindering their applicability in…

In reality, images often exhibit multiple degradations, such as rain and fog at night (triple degradations). However, in many cases, individuals may not want to remove all degradations, for instance, a blurry lens revealing a beautiful…

Blind face restoration from low-quality (LQ) images is a challenging task that requires not only high-fidelity image reconstruction but also the preservation of facial identity. While diffusion models like Stable Diffusion have shown…

High-fidelity and controllable 3D simulation is essential for addressing the long-tail data scarcity in Autonomous Driving (AD), yet existing methods struggle to simultaneously achieve photorealistic rendering and interactive traffic…

This study presents a new image super-resolution (SR) technique based on diffusion inversion, aiming at harnessing the rich image priors encapsulated in large pre-trained diffusion models to improve SR performance. We design a Partial noise…

All-in-one image restoration seeks to recover high-quality images from various types of degradation using a single model, without prior knowledge of the corruption source. However, existing methods often struggle to effectively and…

Diffusion autoencoders (DAEs) are typically formulated as a noise prediction model and trained with a linear-$\beta$ noise schedule that spends much of its sampling steps at high noise levels. Because high noise levels are associated with…

Despite all recent progress, it is still challenging to edit and manipulate natural images with modern generative models. When using Generative Adversarial Network (GAN), one major hurdle is in the inversion process mapping a real image to…

Text-guided non-rigid editing involves complex edits for input images, such as changing motion or compositions within their surroundings. Since it requires manipulating the input structure, existing methods often struggle with preserving…

Single image inverse problem is a notoriously challenging ill-posed problem that aims to restore the original image from one of its corrupted versions. Recently, this field has been immensely influenced by the emergence of deep-learning…

Image restoration faces challenges including ineffective feature fusion, computational bottlenecks and inefficient diffusion processes. To address these, we propose DiffRWKVIR, a novel framework unifying Test-Time Training (TTT) with…

Denoising diffusion models produce high-fidelity image samples by capturing the image distribution in a progressive manner while initializing with a simple distribution and compounding the distribution complexity. Although these models have…

Deep unfolding networks (DUNs) are widely employed in illumination degradation image restoration (IDIR) to merge the interpretability of model-based approaches with the generalization of learning-based methods. However, the performance of…

Changing facial expressions, gestures, or background details may dramatically alter the meaning conveyed by an image. Notably, recent advances in diffusion models greatly improve the quality of image manipulation while also opening the door…

All-in-one medical image restoration (MedIR) aims to address multiple MedIR tasks using a unified model, concurrently recovering various high-quality (HQ) medical images (e.g., MRI, CT, and PET) from low-quality (LQ) counterparts. However,…

Image restoration aims to recover a high-quality clean image from its degraded version. Recent progress in image restoration has demonstrated the effectiveness of All-in-One image restoration models in addressing various unknown…