Measurement Geometry and Design for Trustworthy Generative Inverse Problems

• URL: http://arxiv.org/abs/2606.02309v1
• Date: Mon, 01 Jun 2026 14:28:24 GMT
• Title: Measurement Geometry and Design for Trustworthy Generative Inverse Problems
• Abstract summary: We study generative inverse problems from a measurement-geometry perspective.<n>The central question is whether a fixed measurement operator can distinguish nearby images that are plausible under the generative prior.<n>We introduce a local measurement-manifold compatibility measure that quantifies how well the operator observes prior-relevant tangent directions.
• Score: 9.927046475467204
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generative models are increasingly used as priors for inverse problems, but their ability to produce realistic images creates a basic trust problem: a plausible reconstruction may be supported by the measurements, or it may be filled in by the prior along unobserved directions. This distinction is especially important in medical imaging, where acquisition operators are designed under scan-time, dose, and calibration constraints. We study generative inverse problems from a measurement-geometry perspective. The central question is whether a fixed measurement operator can distinguish nearby images that are plausible under the generative prior, and whether this relationship can guide better measurements. We introduce a local measurement-manifold compatibility measure that quantifies how well the operator observes prior-relevant tangent directions. Under local regularity assumptions, we prove that this quantity controls the stable part of the reconstruction error, while the generative prior controls off-manifold drift. This worst-direction certificate motivates practical fixed and sequential acquisition rules based on overall local volume preservation, including a posterior-cloud design that adapts measurements at test time without training a sampling policy. Across row-sampling, tomographic, and MR acquisition settings, the proposed scores predict failure modes, explain measurement-induced hallucinations, and guide better sampling. In fastMRI Cartesian sampling, posterior-cloud measurement design improves over strong non-learned ACS-preserving baselines, including variable-density and Poisson-like masks.

Related papers

• Conformal Changepoint Localization and Root Cause Analysis with Corrupted Observations [55.76952683833966]
  This paper proposes weighted CONCH (W-CONCH) and weighted CROC (W-CROC) to reduce confidence set size when data may be corrupted.<n>Experiments on image-based and real-world changepoint and root-cause benchmarks show that uncertainty-based weighting substantially reduces confidence set size.
  arXiv  Detail & Related papers  (2026-07-29T05:16:59Z)
• More Data, Worse Decisions? Preference Reversals in Neural Networks under Gram Incompatibility [9.196757973061198]
  Case-Based Decision Theory (CBDT) formalizes the requirement through its composition axiom.<n>We study when this property holds for fixed-representation neural networks with ordinary least squares (OLS) output heads.<n>We develop a three-stage audit that traces strict pairwise reversals through decision changes to task-defined utility loss.
  arXiv  Detail & Related papers  (2026-07-28T18:52:47Z)
• Phase-space entropy at acquisition reflects downstream learnability [54.4100065023873]
  We propose an acquisition-level scalar $S_mathcal B$ based on instrument-resolved phase space.<n>We show theoretically that (S_mathcal B) correctly identifies the phase-space coherence of periodic sampling.<n>$|S_mathcal B|$ consistently ranks sampling geometries and predicts downstream reconstruction/recognition difficulty emphwithout training.
  arXiv  Detail & Related papers  (2025-12-22T10:03:51Z)
• Measurement-Constrained Sampling for Text-Prompted Blind Face Restoration [60.45423400845294]
  Blind face restoration (BFR) may correspond to multiple plausible high-quality (HQ) reconstructions under extremely low-quality (LQ) inputs.<n>We propose a Measurement-Constrained Sampling (MCS) approach that enables diverse LQ face reconstructions conditioned on different textual prompts.
  arXiv  Detail & Related papers  (2025-11-18T07:44:54Z)
• Towards Distribution-Shift Uncertainty Estimation for Inverse Problems with Generative Priors [4.085626952545055]
  Gene models have shown strong potential as data-driven priors for solving inverse problems.<n>We propose an instance-level, calibration-free uncertainty indicator that is sensitive to distribution shift.<n>Our proposed indicator is efficiently computable for any computational imaging inverse problem.
  arXiv  Detail & Related papers  (2025-10-13T02:58:26Z)
• Measurement-Guided Consistency Model Sampling for Inverse Problems [2.217547045999963]
  Consistency models enable high-quality generation in a single or only a few steps.<n>We present a modified consistency sampling approach tailored for inverse problem reconstruction.
  arXiv  Detail & Related papers  (2025-10-02T16:53:07Z)
• Generative Model Inversion Through the Lens of the Manifold Hypothesis [98.37040155914595]
  Model inversion attacks (MIAs) aim to reconstruct class-representative samples from trained models.<n>Recent generative MIAs utilize generative adversarial networks to learn image priors that guide the inversion process.
  arXiv  Detail & Related papers  (2025-09-24T14:39:25Z)
• Solving Inverse Problems with FLAIR [68.87167940623318]
  We present FLAIR, a training-free variational framework that leverages flow-based generative models as prior for inverse problems.<n>Results on standard imaging benchmarks demonstrate that FLAIR consistently outperforms existing diffusion- and flow-based methods in terms of reconstruction quality and sample diversity.
  arXiv  Detail & Related papers  (2025-06-03T09:29:47Z)
• pcaGAN: Improving Posterior-Sampling cGANs via Principal Component Regularization [11.393603788068777]
  In ill-posed imaging inverse problems, there can exist many hypotheses that fit both the observed measurements and prior knowledge of the true image. We propose a fast and accurate posterior-sampling conditional generative adversarial network (cGAN) that, through a novel form of regularization, aims for correctness in the posterior mean.
  arXiv  Detail & Related papers  (2024-11-01T14:09:28Z)
• Task-Driven Uncertainty Quantification in Inverse Problems via Conformal Prediction [11.393603788068777]
  In imaging inverse problems, one seeks to recover an image from missing/corrupted measurements. Motivated by applications where the recovered image is used for a downstream task, we propose a task-centered approach to uncertainty quantification.
  arXiv  Detail & Related papers  (2024-05-28T18:49:17Z)
• MOSAIC: Masked Optimisation with Selective Attention for Image Reconstruction [0.5541644538483947]
  We propose a novel compressive sensing framework to reconstruct images given any random selection of measurements. MOSAIC incorporates an embedding technique to efficiently apply attention mechanisms on an encoded sequence of measurements. A range of experiments validate our proposed architecture as a promising alternative for existing CS reconstruction methods.
  arXiv  Detail & Related papers  (2023-06-01T17:05:02Z)
• Self-Supervised Training with Autoencoders for Visual Anomaly Detection [61.62861063776813]
  We focus on a specific use case in anomaly detection where the distribution of normal samples is supported by a lower-dimensional manifold. We adapt a self-supervised learning regime that exploits discriminative information during training but focuses on the submanifold of normal examples. We achieve a new state-of-the-art result on the MVTec AD dataset -- a challenging benchmark for visual anomaly detection in the manufacturing domain.
  arXiv  Detail & Related papers  (2022-06-23T14:16:30Z)
• Optimal Change-Point Detection with Training Sequences in the Large and Moderate Deviations Regimes [72.68201611113673]
  This paper investigates a novel offline change-point detection problem from an information-theoretic perspective. We assume that the knowledge of the underlying pre- and post-change distributions are not known and can only be learned from the training sequences which are available.
  arXiv  Detail & Related papers  (2020-03-13T23:39:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.