GPARA: Graph-Posterior-Aligned Refinement and Active Acquisition for Grounding Diffusion Priors

2026-09-28

AI Summary

This study addresses the challenges of jointly optimizing measurement acquisition and reconstruction refinement, computational redundancy, and insufficient posterior geometric capture when employing frozen diffusion priors for active grounding. To this end, we propose a reusable posterior response operator based on a residual graph surrogate. The method incorporates bounded learning with residual calibration to compensate for surrogate mismatch, achieves efficient joint optimization through single-pass integrated reconditioning, and establishes consistency between analytic ranking and expected improvement. Experiments demonstrate that the proposed approach significantly outperforms baselines in both refinement quality and active acquisition performance across physical field and visual reconstruction tasks. Furthermore, ablation studies validate the complementary contributions of individual modules.

Abstract

Active grounding of a frozen diffusion prior requires jointly determining where new measurements should be taken and how they should be used to refine the current reconstruction. Posterior-ensemble-based methods can estimate acquisition utility from generated samples, but require repeated ensemble generation as observations accumulate and capture posterior geometry only through empirical statistics. This paper proposes GPARA, which learns a context-dependent graph surrogate over diffusion prediction residuals, inducing an explicitly reusable posterior response operator that propagates measurement innovations to unobserved variables and evaluates candidate measurements through weighted posterior-risk reduction. Under the matched surrogate, we show that the same response operator also determines expected one-step acquisition benefit and yields an analytic ranking consistent with expected reconstruction improvement. A bounded learned residual calibrates the analytic utility to account for surrogate mismatch, while a small prior ensemble is generated once and reconditioned to update risk weights without repeated diffusion posterior sampling during acquisition. Experiments on two reconstruction tasks spanning physical field and computer vision show consistent improvements in refinement and active acquisition over the evaluated baselines. Ablations further support the complementary roles of step-wise graph refinement, adaptive risk weighting, and analytically anchored calibration.

Problem

• diffusion priors
• active acquisition
• posterior estimation
• reconstruction refinement
• grounding

Innovation

• Graph Surrogate
• Active Acquisition
• Diffusion Priors
• Posterior Response Operator
• Risk Calibration