Log på
indsigt - Super-Resolution Techniques
Adaptive Multi-modal Fusion for Blind Image Super-Resolution
The author introduces a framework for Adaptive Multi-modal Fusion of Spatially Variant Kernel Refinement with Diffusion Model for Blind Image Super-Resolution, addressing the limitations of existing diffusion-based methodologies and proposing innovative modules to enhance image super-resolution.
CasSR: Activating Image Power for Real-World Image Super-Resolution
Proposing CasSR, a novel method for image super-resolution that leverages image activation and multiple attention mechanisms to enhance fidelity and quality.
Self-Adaptive Reality-Guided Diffusion for Artifact-Free Super-Resolution Analysis
Proposing Self-Adaptive Reality-Guided Diffusion (SARGD) for artifact-free super-resolution, enhancing image quality and reducing inference time.
Blind Image Super-Resolution with Spatially Variant Kernel Refinement and Diffusion Model
Blind image super-resolution is enhanced by integrating depth information and spatially variant blur kernels through the SSR framework.