Posterior Continuation with Noise-Conditioned Frequency Exposure for Diffusion Inverse Problems
Diffusion posterior sampling solves inverse problems by combining a pretrained diffusion prior with measurement-consistency guidance. However, full-band guidance can be unreliable at high noise levels, where clean estimates contain score-induced errors and high-frequency measurement directions are weakly identifiable. We argue that posterior guidance should expose measurement frequencies according to the instantaneous diffusion noise level. Based on this principle, we propose a posterior continuation framework that constructs a family of intermediate posteriors whose likelihood emphasizes currently reliable frequency bands and gradually returns to full-band consistency. We instantiate this framework with a stabilized sampler that combines a diffusion predictor, frequency-limited likelihood refinement, and a Haar-domain commitment rule that commits reliable coarse corrections while deferring weakly identifiable details. Across super-resolution, inpainting, and deblurring, our method achieves competitive-to-state-of-the-art restoration performance, including up to 5 dB PSNR improvement on motion deblurring over strong baselines in evaluations on FFHQ and ImageNet.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Sparse modeling approach to analytical continuation of imaginary-time quantum Monte Carlo data
A new approach of solving the ill-conditioned inverse problem for analytical continuation is proposed. The root of the problem lies in the fact that even tiny noise of imaginary-time input data has a serious impact on th…
Projected Regression Methods for Inverting Fredholm Integrals: Formalism and Application to Analytical Continuation
We present a machine learning approach to the inversion of Fredholm integrals of the first kind. The approach provides a natural regularization in cases where the inverse of the Fredholm kernel is ill-conditioned. It als…
BIG-bench Machine LearningregressionCorrecting Neural Operator Spectral Bias via Diffusion Posterior Sampling with Sparse Observations
Neural operator surrogates (NO) approximate PDE solutions orders of magnitude faster than numerical solvers, but suffer from spectral bias: high-frequency content is systematically attenuated, limiting reliability where …
Learning Spatially Varying Pixel Exposures for Motion Deblurring
Computationally removing the motion blur introduced by camera shake or object motion in a captured image remains a challenging task in computational photography. Deblurring methods are often limited by the fixed global e…
DeblurringExposure Bias Can Alleviate Itself via Directional and Frequency Rectification in Flow Matching
Flow Matching (FM) has achieved remarkable generative performance, yet it suffers from exposure bias due to discrepancies between training and inference. Existing mitigation strategies typically rely on static constraint…