PRISM: Prior Rectification and Uncertainty-Aware Structure Modeling for Diffusion-Based Text Image Super-Resolution
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.
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: Position-encoded Regressive Inverse Spectral Model for Multilayer Thin-Film Design
PRISM is a decoder-only autoregressive transformer that solves the inverse problem of multilayer thin-film optical coating design by jointly predicting material selection and thickness, achieving state-of-the-art performance with significantly smaller models.
PRISM: A Geometric Risk Bound that Decomposes Drift into Scale, Shape, and Head
This paper introduces PRISM, a geometric risk bound that decomposes model drift in post-training LLM variants into scale, shape, and head axes to diagnose specific failure modes like quantization errors or catastrophic forgetting.
PRISM: Perception Reasoning Interleaved for Sequential Decision Making
This paper introduces PRISM, a framework that integrates Vision-Language Models and Large Language Models through a dynamic question-answering pipeline to improve sequential decision-making in embodied AI tasks.
PRISM: A Benchmark for Programmatic Spatial-Temporal Reasoning
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.
Nemotron-Labs-Diffusion-Image: Advancing Masked Discrete Diffusion for High-Resolution Image Synthesis
This paper proposes Nemotron-Labs-Diffusion-Image, a masked discrete diffusion model for high-resolution text-to-image synthesis, introducing a token-editing mechanism and grouped cross-entropy objective to improve token refinement and training efficiency.