Get Started
Home
Topics
Search
Library
Research questionHow can diffusion-based image restoration adapt to spatially varying degradations without artifacts or redundant sampling?Fixed data constraints and uniform diffusion schedules can mishandle regions with different degradation levels, causing structural artifacts and lost detail while spending computation on unnecessarily fine sampling steps.
Computer Vision
Diffusion Models
Image & Video Processing
Inference Optimization
Machine Learning
Latest papersRecent research connected to this question, newest first.Local Epistemic Uncertainty Guided Active Sampling for Plug-and-play Diffusive Image RestorationThe source addresses plug-and-play diffusion-model image restoration. It describes pixel-wise uncertainty for spatially adaptive prior strength and uncertainty-based trajectory pruning for faster sampling, with claims of strict data consistency, bounded skip-sampling error, compatibility with multiple restoration baselines, improved results, and negligible memory overhead.research paper · Sep 2, 2026
Related questions
How can diffusion-based image restoration enforce data consistency efficiently under accelerated sampling?How can diffusion models preserve fine perceptual detail when reconstructing high-resolution images from low-resolution inputs?How can diffusion priors reconstruct images from linear measurements while balancing fidelity and diversity?How can few-step diffusion defer high-resolution denoising without causing transition artifacts?