Frequency Decoupled Framework for Screen Content Image Super-Resolution

2026-06-08

AI Summary

Existing implicit neural representation methods for screen content image super-resolution often overlook frequency characteristics, limiting their reconstruction performance. To address this, this work proposes an amplitude-phase decoupling framework that explicitly models periodic structures and global contextual continuity. Specifically, an amplitude clustering module extracts repetitive patterns, while a phase consistency-based self-attention mechanism captures long-range structural coherence. These representations are effectively fused through an oscillatory anharmonic implicit fitting network (OAIF-Net). The complete approach—comprising the Amplitude-Phase Fitting Network (APFN), Amplitude Clustering Module (ACM), Phase Consistency Self-Attention (PCSA), and OAIF-Net—achieves state-of-the-art performance across four public benchmarks under multi-scale super-resolution settings. Ablation studies further confirm the individual contributions of each component in modeling periodic textures and coherent spatial contexts.

Abstract

Methods based on implicit neural representations have demonstrated superior performance in Screen Content Image Super-Resolution (SCISR) . However, they overlooked the inherent frequency characteristics, leading to suboptimal performance. We propose a frequency decoupled framework (FDF) that rethinks SCISR from a phasor perspective by capturing structured energy in amplitude and relational continuity in phase, and jointly exploiting them with bespoke implicit representations to faithfully recover the regular textures and global configuration of Screen Content Image (SCI). Amplitude-Phase Factorization Network (APFN) first separates images into amplitude and phase streams, where Amplitude Clustering Module (ACM) organizes sparse yet high-energy amplitude responses into representative prototypes for periodic pattern extraction, while Phase Consistency Self-Attention (PCSA) progressively reinforces configuration through continuous consistency propagation. And Oscillation-Anharmonic Implicit Fitting Network (OAIF-Net) integrates periodic and coherent implicit representations for efficient exploitation of the periodic patterns and coherent context embedded in SCI. Experimental results show FDF achieves state-of-the-art SCISR performance at multiple scales across four public SCI datasets. Ablation experiments further demonstrate the effectiveness of each component in extracting and exploiting periodic patterns and coherent context.

Problem

• Screen Content Image Super-Resolution
• frequency characteristics
• implicit neural representations
• periodic patterns
• coherent context

Innovation

• frequency decoupling
• implicit neural representation
• amplitude-phase factorization
• screen content image super-resolution
• phase consistency