SFP: Real-World Scene Recovery Using Spatial and Frequency Priors

2025-12-09

AI Summary

Existing scene restoration methods often rely on a single prior or are trained exclusively on synthetic data, leading to poor generalization under real-world complex degradations. To address this, we propose a Spatial-Frequency Dual Prior (SFP) framework. Our method introduces, for the first time, spectral directional projection of the degraded image in the spatial domain as a transmission prior; establishes dual frequency-domain priors—inter-channel DC-component mean approximation and radial low-frequency energy ratio constancy; and designs three core components: spatial-domain transmission map estimation, frequency-domain adaptive masking enhancement, and multi-domain feature weighting fusion. Extensive experiments across diverse real-world degradation scenarios demonstrate that SFP consistently outperforms state-of-the-art methods, achieving significant improvements in both visual quality and quantitative metrics (PSNR/SSIM). Moreover, it exhibits strong robustness and broad applicability across varying degradation types.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multi-instance/Multi-view Learning
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Scene recovery serves as a critical task for various computer vision applications. Existing methods typically rely on a single prior, which is inherently insufficient to handle multiple degradations, or employ complex network architectures trained on synthetic data, which suffer from poor generalization for diverse real-world scenarios. In this paper, we propose Spatial and Frequency Priors (SFP) for real-world scene recovery. In the spatial domain, we observe that the inverse of the degraded image exhibits a projection along its spectral direction that resembles the scene transmission. Leveraging this spatial prior, the transmission map is estimated to recover the scene from scattering degradation. In the frequency domain, a mask is constructed for adaptive frequency enhancement, with two parameters estimated using our proposed novel priors. Specifically, one prior assumes that the mean intensity of the degraded image's direct current (DC) components across three channels in the frequency domain closely approximates that of each channel in the clear image. The second prior is based on the observation that, for clear images, the magnitude of low radial frequencies below 0.001 constitutes approximately 1% of the total spectrum. Finally, we design a weighted fusion strategy to integrate spatial-domain restoration, frequency-domain enhancement, and salient features from the input image, yielding the final recovered result. Extensive evaluations demonstrate the effectiveness and superiority of our proposed SFP for scene recovery under various degradation conditions.

Problem

• Recovers scenes from multiple real-world degradations
• Estimates transmission map using spatial prior
• Enhances frequencies adaptively with novel priors

Innovation

• Uses spatial prior for transmission map estimation
• Applies frequency-domain adaptive enhancement with novel priors
• Integrates spatial, frequency, and salient features via weighted fusion