aiqbench analysis
This research introduces CPF-DDNM, an inference-time strategy that enhances diffusion models for recovering unobservable image structures by fusing consecutive posterior estimates without retraining. By leveraging null-space decomposition, the method geometrically separates measurement-consistent components from prior-driven corrections to improve performance in tasks like sparse-view CT and medical super-resolution. This advancement directly addresses limitations in standard diffusion samplers within the context of solving ill-posed imaging inverse problems using learned priors.
Consecutive Posterior Fusion for Diffusive Recovery of Unobservable Image Structures
arXiv:2610.03261v1 Announce Type: cross Abstract: Solving severely ill-posed imaging inverse problems requires recovering image structures that are unobservable or weakly constrained by the measurements. Diffusion models provide expressive learned priors for inferring such missing information, while posterior sampling incorporates measurement consistency along the reverse process. Standard diffusion posterior samplers, however, rely on instantaneous measurement-aware estimates, without explicitly exploiting information carried by previous posterior corrections. We introduce Consecutive Posterior Fusion Denoising Diffusion Null-Space Models (CPF-DDNM), an inference-time strategy that fuses consecutive measurement-aware estimates to improve the diffusive recovery of unobservable image structures, without requiring retraining or additional denoiser evaluations. We instantiate this principle within DDNM, whose range/null-space decomposition reveals that consecutive fusion preserves the measurement-determined component while acting exclusively on the prior-driven null-space estimate. We thus provide a geometric interpretation of CPF-DDNM and a local error analysis that characterizes the optimal time-dependent fusion coefficient, including the extrapolative regime. Experiments on sparse-view and simulated low-dose computed tomography, as well as medical image super-resolution, show consistent improvements over DDNM and competitive performance against diffusion-based inverse solvers.
Abstract:Solving severely ill-posed imaging inverse problems requires recovering image structures that are unobservable or weakly constrained by the measurements. Diffusion models provide expressive learned priors for inferring such missing information, while posterior sampling incorporates measurement consistency along the reverse process. Standard diffusion posterior samplers, however, rely on instantaneous measurement-aware estimates, without explicitly exploiting information carried by previous posterior corrections. We introduce Consecutive Posterior Fusion Denoising Diffusion Null-Space Models (CPF-DDNM), an inference-time strategy that fuses consecutive measurement-aware estimates to improve the diffusive recovery of unobservable image structures, without requiring retraining or additional denoiser evaluations. We instantiate this principle within DDNM, whose range/null-space decomposition reveals that consecutive fusion preserves the measurement-determined component while acting exclusively on the prior-driven null-space estimate. We thus provide a geometric interpretation of CPF-DDNM and a local error analysis that characterizes the optimal time-dependent fusion coefficient, including the extrapolative regime. Experiments on sparse-view and simulated low-dose computed tomography, as well as medical image super-resolution, show consistent improvements over DDNM and competitive performance against diffusion-based inverse solvers.
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
arXiv:2610.03261 [cs.CV]
(or arXiv:2610.03261v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2610.03261 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 268 words
Related coverage
L2G-Map: Local-to-Global Mapping via Hierarchical Diffusion Refinement and Elliptical Bayesian Fusion
arXiv · Sep 9, 2026
SRUG: A Fusion-Driven Generator Network for Medical Image Translation
arXiv · Oct 10, 2026
[AINews] TypeSafe/Jev at >$100M ARR, $7.5B valuation 3 weeks after launch
Latent Space · Oct 10, 2026
Digital States 2026: AI Moves From Experiment to Infrastructure
govtech.com · Sep 24, 2026