CircleFlow: Flow-Guided Camera Blur Estimation using a Circle Grid Target

2025-11-30

AI Summary

Accurate estimation of spatially varying, anisotropic point spread functions (PSFs) remains challenging in camera motion blur. To address this, we propose a PSF decoupling modeling framework integrating annular grid calibration with optical flow guidance. Our method employs optical flow-driven subpixel edge localization, binary brightness priors, and energy-normalized implicit neural representations to achieve geometry-aware PSF modeling. Crucially, we formulate the first differentiable demosaic-based joint optimization of both the latent sharp image and spatially varying blur kernels, ensuring strict physical consistency. Extensive experiments on synthetic and real-world datasets demonstrate state-of-the-art performance, with significant improvements in PSF estimation accuracy, robustness against noise and misalignment, and practical calibration feasibility.

Technology Category

• Computer Vision: Computational Photography, Image & Video Synthesis
• Intelligent Robots: State Estimation
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

The point spread function (PSF) serves as a fundamental descriptor linking the real-world scene to the captured signal, manifesting as camera blur. Accurate PSF estimation is crucial for both optical characterization and computational vision, yet remains challenging due to the inherent ambiguity and the ill-posed nature of intensity-based deconvolution. We introduce CircleFlow, a high-fidelity PSF estimation framework that employs flow-guided edge localization for precise blur characterization. CircleFlow begins with a structured capture that encodes locally anisotropic and spatially varying PSFs by imaging a circle grid target, while leveraging the target's binary luminance prior to decouple image and kernel estimation. The latent sharp image is then reconstructed through subpixel alignment of an initialized binary structure guided by optical flow, whereas the PSF is modeled as an energy-constrained implicit neural representation. Both components are jointly optimized within a demosaicing-aware differentiable framework, ensuring physically consistent and robust PSF estimation enabled by accurate edge localization. Extensive experiments on simulated and real-world data demonstrate that CircleFlow achieves state-of-the-art accuracy and reliability, validating its effectiveness for practical PSF calibration.

Problem

• Estimates camera blur via point spread function
• Uses circle grid target for precise blur characterization
• Jointly optimizes image and kernel in demosaicing framework

Innovation

• Flow-guided edge localization for blur characterization
• Circle grid target encodes anisotropic PSFs spatially
• Differentiable framework jointly optimizes image and kernel