相关论文: The Power of Context: How Multimodality Improves I…
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…
Existing super-resolution (SR) models primarily focus on restoring local texture details, often neglecting the global semantic information within the scene. This oversight can lead to the omission of crucial semantic details or the…
Single image super resolution is a very important computer vision task, with a wide range of applications. In recent years, the depth of the super-resolution model has been constantly increasing, but with a small increase in performance, it…
Recent data-driven image colorization methods have enabled automatic or reference-based colorization, while still suffering from unsatisfactory and inaccurate object-level color control. To address these issues, we propose a new method…
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…
Non-visual imaging sensors are widely used in the industry for different purposes. Those sensors are more expensive than visual (RGB) sensors, and usually produce images with lower resolution. To this end, Cross-Modality Super-Resolution…
High-resolution imagery is often hindered by limitations in sensor technology, atmospheric conditions, and costs. Such challenges occur in satellite remote sensing, but also with handheld cameras, such as our smartphones. Hence,…
Despite recent advances, single-image super-resolution (SR) remains challenging, especially in real-world scenarios with complex degradations. Diffusion-based SR methods, particularly those built on Stable Diffusion, leverage strong…
Single image super-resolution (SISR) is a notoriously challenging ill-posed problem, which aims to obtain a high-resolution (HR) output from one of its low-resolution (LR) versions. To solve the SISR problem, recently powerful deep learning…
With the advent of Generative AI, Single Image Super-Resolution (SISR) quality has seen substantial improvement, as the strong priors learned by Text-2-Image Diffusion (T2IDiff) Foundation Models (FM) can bridge the gap between…
Diffusion models are highly regarded for their controllability and the diversity of images they generate. However, class-conditional generation methods based on diffusion models often focus on more common categories. In large-scale…
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…
Self-supervised cross-modal super-resolution (SR) can overcome the difficulty of acquiring paired training data, but is challenging because only low-resolution (LR) source and high-resolution (HR) guide images from different modalities are…
Recently, large-scale diffusion models, e.g., Stable diffusion and DallE2, have shown remarkable results on image synthesis. On the other hand, large-scale cross-modal pre-trained models (e.g., CLIP, ALIGN, and FILIP) are competent for…
Large-scale pre-trained diffusion models have been extensively adopted for real-world image Super-Resolution because of their powerful generative priors through textual guidance. However, when super-resolving high-resolution images with…
Image synthesis approaches, e.g., generative adversarial networks, have been popular as a form of data augmentation in medical image analysis tasks. It is primarily beneficial to overcome the shortage of publicly accessible data and…
Multi-image super-resolution (MISR) can achieve higher image quality than single-image super-resolution (SISR) by aggregating sub-pixel information from multiple spatially shifted frames. Among MISR tasks, burst super-resolution (BurstSR)…
The colorization of grayscale images is a complex and subjective task with significant challenges. Despite recent progress in employing large-scale datasets with deep neural networks, difficulties with controllability and visual quality…
Assuming a known degradation model, the performance of a learned image super-resolution (SR) model depends on how well the variety of image characteristics within the training set matches those in the test set. As a result, the performance…
We propose Context Diffusion, a diffusion-based framework that enables image generation models to learn from visual examples presented in context. Recent work tackles such in-context learning for image generation, where a query image is…