PRISM: Prior Rectification and Uncertainty-Aware Structure Modeling for Diffusion-Based Text Image Super-Resolution

TL;DR

PRISM is a diffusion-based framework for text image super-resolution that improves global prior rectification and local structure refinement, enhancing readability and accuracy in degraded images.

Contribution

It introduces Flow-Matching Prior Rectification and a Structure-guided Uncertainty-aware Residual Encoder for improved text super-resolution.

Findings

Achieves state-of-the-art performance on synthetic and real-world benchmarks.

Provides millisecond-level inference speed.

Effectively restores text structure and readability in severely degraded images.

Abstract

Text image super-resolution (Text-SR) requires more than visually plausible detail synthesis: slight errors in stroke topology may alter character identity and break readability. Existing methods improve text fidelity with stronger recognition-based or generative priors, yet they still face two unresolved challenges under severe degradation: the text condition extracted from low-quality inputs can itself be unreliable, and a plausible global prior does not fully determine fine-grained stroke boundaries. We present PRISM, a single-step diffusion-based Text-SR framework that addresses these two challenges through Flow-Matching Prior Rectification (FMPR) and a Structure-guided Uncertainty-aware Residual Encoder (SURE). FMPR constructs a privileged training-time prior from paired low-quality/high-quality latents and learns a flow matching that transports degraded embeddings toward this restoration-oriented prior space, yielding more accurate and reliable global text guidance. SURE further predicts uncertainty-aware structural residuals to selectively absorb reliable local boundary evidence while suppressing ambiguous stroke cues. Together, these components enable explicit global prior rectification and local structure refinement within a single diffusion restoration pass. Experiments on both synthetic and real-world benchmarks show that PRISM achieves state-of-the-art performance with millisecond-level inference. Our dataset and code will be available at https://github.com/faithxuz/PRISM.