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

Hugging Face Daily Papers Papers

Summary

PRISM is a diffusion-based framework for text image super-resolution that uses flow-matching prior rectification and uncertainty-aware residual encoding to improve accuracy under severe degradation, achieving state-of-the-art performance with millisecond-level inference.

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.
Original Article
View Cached Full Text

Cached at: 05/15/26, 08:24 AM

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

Source: https://huggingface.co/papers/2605.13027 Published on May 13

·

Submitted byhttps://huggingface.co/young13579

张扬on May 15

Abstract

PRISM is a diffusion-based text super-resolution framework that improves accuracy under severe degradation by using flow-matching prior rectification and uncertainty-aware residual encoding.

Text image super-resolution (Text-SR) requires more than visually plausible detail synthesis: slight errors instroke topologymay 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: thetext conditionextracted from low-quality inputs can itself be unreliable, and a plausibleglobal priordoes not fully determine fine-grained stroke boundaries. We present PRISM, a single-stepdiffusion-based Text-SRframework that addresses these two challenges throughFlow-Matching Prior Rectification(FMPR) and aStructure-guided Uncertainty-aware Residual Encoder(SURE).FMPRconstructs a privileged training-time prior from paired low-quality/high-quality latents and learns aflow matchingthat transports degraded embeddings toward this restoration-oriented prior space, yielding more accurate and reliable global text guidance.SUREfurther predicts uncertainty-aware structural residuals to selectively absorb reliable local boundary evidence while suppressing ambiguous stroke cues. Together, these components enable explicitglobal priorrectification andlocal structure refinementwithin 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.

View arXiv pageView PDFAdd to collection

Get this paper in your agent:

hf papers read 2605\.13027

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2605.13027 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2605.13027 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2605.13027 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

PRISM: A Benchmark for Programmatic Spatial-Temporal Reasoning

arXiv cs.AI

PRISM is a large-scale benchmark of 10,372 human-calibrated instruction-code pairs for evaluating programmatic video generation, with a funnel-style framework of four metrics. Evaluation of seven LLMs reveals a significant gap between code executability and spatial coherence.