.</p>\n","updatedAt":"2026-05-15T05:20:36.919Z","author":{"_id":"661b39b18ad066992415e2af","avatarUrl":"/avatars/8854bed4cf07d619555ab6e071be49ba.svg","fullname":"张扬","name":"young13579","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"fr","probability":0.32275810837745667},"editors":["young13579"],"editorAvatarUrls":["/avatars/8854bed4cf07d619555ab6e071be49ba.svg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2605.13027","authors":[{"_id":"6a06ac13b1a8cbabc9f099ed","name":"Zihang Xu","hidden":false},{"_id":"6a06ac13b1a8cbabc9f099ee","name":"Xiaoyang Liu","hidden":false},{"_id":"6a06ac13b1a8cbabc9f099ef","name":"Zheng Chen","hidden":false},{"_id":"6a06ac13b1a8cbabc9f099f0","name":"Yulun Zhang","hidden":false},{"_id":"6a06ac13b1a8cbabc9f099f1","name":"Xiaokang Yang","hidden":false}],"publishedAt":"2026-05-13T00:00:00.000Z","submittedOnDailyAt":"2026-05-15T00:00:00.000Z","title":"PRISM: Prior Rectification and Uncertainty-Aware Structure Modeling for Diffusion-Based Text Image Super-Resolution","submittedOnDailyBy":{"_id":"661b39b18ad066992415e2af","avatarUrl":"/avatars/8854bed4cf07d619555ab6e071be49ba.svg","isPro":false,"fullname":"张扬","user":"young13579","type":"user","name":"young13579"},"summary":"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.","upvotes":4,"discussionId":"6a06ac14b1a8cbabc9f099f2","ai_summary":"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.","ai_keywords":["diffusion-based Text-SR","Flow-Matching Prior Rectification","FMPR","Structure-guided Uncertainty-aware Residual Encoder","SURE","flow matching","latent space","text condition","stroke topology","global prior","local structure refinement"],"organization":{"_id":"652faff917096ceb6bf53f3f","name":"deepseek-ai","fullname":"DeepSeek","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/6538815d1bdb3c40db94fbfa/xMBly9PUMphrFVMxLX4kq.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"63c1699e40a26dd2db32400d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63c1699e40a26dd2db32400d/3N0-Zp8igv8-52mXAdiiq.jpeg","isPro":false,"fullname":"Chroma","user":"Chroma111","type":"user"},{"_id":"655e4c26d5c0d3db535cdd66","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/655e4c26d5c0d3db535cdd66/IjYjuy2goiaHG08mFiFmU.jpeg","isPro":false,"fullname":"Lincoln","user":"Presidentlin","type":"user"},{"_id":"661ab1f1fa3b144a381fa454","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/661ab1f1fa3b144a381fa454/IlpZBb9NCjo7ntFwMIH53.png","isPro":true,"fullname":"Urro","user":"urroxyz","type":"user"},{"_id":"620783f24e28382272337ba4","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/620783f24e28382272337ba4/zkUveQPNiDfYjgGhuFErj.jpeg","isPro":false,"fullname":"GuoLiangTang","user":"Tommy930","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"652faff917096ceb6bf53f3f","name":"deepseek-ai","fullname":"DeepSeek","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/6538815d1bdb3c40db94fbfa/xMBly9PUMphrFVMxLX4kq.png"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2605/2605.13027.md"}">
PRISM: Prior Rectification and Uncertainty-Aware Structure Modeling for Diffusion-Based Text Image Super-Resolution
Published on May 13
· Submitted by 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.
AI-generated summary
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.
Community
Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images
Cite arxiv.org/abs/2605.13027 in a model README.md to link it from this page.
Cite arxiv.org/abs/2605.13027 in a dataset README.md to link it from this page.
Cite arxiv.org/abs/2605.13027 in a Space README.md to link it from this page.
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.