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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Xu, Zihang, Liu, Xiaoyang, Chen, Zheng, Zhang, Yulun, Yang, Xiaokang
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909039390097408
author Xu, Zihang
Liu, Xiaoyang
Chen, Zheng
Zhang, Yulun
Yang, Xiaokang
author_facet Xu, Zihang
Liu, Xiaoyang
Chen, Zheng
Zhang, Yulun
Yang, Xiaokang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_13027
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle PRISM: Prior Rectification and Uncertainty-Aware Structure Modeling for Diffusion-Based Text Image Super-Resolution
Xu, Zihang
Liu, Xiaoyang
Chen, Zheng
Zhang, Yulun
Yang, Xiaokang
Computer Vision and Pattern Recognition
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.
title PRISM: Prior Rectification and Uncertainty-Aware Structure Modeling for Diffusion-Based Text Image Super-Resolution
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.13027