Related papers: ReFIR: Grounding Large Restoration Models with Ret…
Handling test-time unknown degradation is the major challenge in Blind Image Restoration (BIR), necessitating high model generalization. An effective strategy is to incorporate prior knowledge, either from human input or generative model.…
Illumination degradation image restoration (IDIR) techniques aim to improve the visibility of degraded images and mitigate the adverse effects of deteriorated illumination. Among these algorithms, diffusion model (DM)-based methods have…
Reference-based image super-resolution (RefSR) is a promising SR branch and has shown great potential in overcoming the limitations of single image super-resolution. While previous state-of-the-art RefSR methods mainly focus on improving…
Recent advancements in image restoration increasingly employ conditional latent diffusion models (CLDMs). While these models have demonstrated notable performance improvements in recent years, this work questions their suitability for IR…
Image super-resolution pursuits reconstructing high-fidelity high-resolution counterpart for low-resolution image. In recent years, diffusion-based models have garnered significant attention due to their capabilities with rich prior…
Generative artificial intelligence holds significant potential for abuse, and generative image detection has become a key focus of research. However, existing methods primarily focused on detecting a specific generative model and…
Reconstructing visual stimuli from fMRI signals is a central challenge bridging machine learning and neuroscience. Recent diffusion-based methods typically map fMRI activity to a single high-level embedding, using it as fixed guidance…
High-resolution (HR) image perception remains a key challenge in multimodal large language models (MLLMs). To overcome the limitations of existing methods, this paper shifts away from prior dedicated heuristic approaches and revisits the…
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),…
Large Language Models (LLMs) have been found to have difficulty knowing they do not possess certain knowledge and tend to provide specious answers in such cases. Retrieval Augmentation (RA) has been extensively studied to mitigate LLMs'…
Recent advancements in Large Vision Language Models (LVLMs) have revolutionized how machines understand and generate textual responses based on visual inputs, yet they often produce "hallucinatory" outputs that misinterpret visual…
The objective of Content-Based Image Retrieval (CBIR) methods is essentially to extract, from large (image) databases, a specified number of images similar in visual and semantic content to a so-called query image. To bridge the semantic…
Image restoration aims to recover degraded images. However, existing diffusion-based restoration methods, despite great success in natural image restoration, often struggle to faithfully reconstruct textual regions in degraded images. Those…
Most recent extreme rescaling methods struggle to preserve semantically consistent structures and produce realistic details, due to the severely ill-posed nature of low- to high-resolution mapping under scaling factors of $16\times$ or…
Image rescaling is a commonly used bidirectional operation, which first downscales high-resolution images to fit various display screens or to be storage- and bandwidth-friendly, and afterward upscales the corresponding low-resolution…
Large Language Models (LLMs) showcase impressive capabilities but encounter challenges like hallucination, outdated knowledge, and non-transparent, untraceable reasoning processes. Retrieval-Augmented Generation (RAG) has emerged as a…
Existing fine-grained image retrieval (FGIR) methods predominantly rely on supervision from predefined categories to learn discriminative representations for retrieving fine-grained objects. However, they inadvertently introduce…
Generative image reconstruction algorithms such as measurement conditioned diffusion models are increasingly popular in the field of medical imaging. These powerful models can transform low signal-to-noise ratio (SNR) inputs into outputs…
Low Dynamic Range (LDR) to High Dynamic Range (HDR) image translation is a fundamental task in many computational vision problems. Numerous data-driven methods have been proposed to address this problem; however, they lack explicit modeling…
The emergence of Large Language Models (LLMs) has revolutionized how users access information, shifting from traditional search engines to direct question-and-answer interactions with LLMs. However, the widespread adoption of LLMs has…