{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/ncap-scene-text-image-super-resolution-with","title":"NCAP: Scene Text Image Super-Resolution with Non-CAtegorical Prior","arxiv_id":"2504.00410","date":"2025-04-01","proceeding":null,"authors":["Dongwoo Park","Suk Pil Ko"],"abstract":"Scene text image super-resolution (STISR) enhances the resolution and quality of low-resolution images. Unlike previous studies that treated scene text images as natural images, recent methods using a text prior (TP), extracted from a pre-trained text recognizer, have shown strong performance. However, two major issues emerge: (1) Explicit categorical priors, like TP, can negatively impact STISR if incorrect. We reveal that these explicit priors are unstable and propose replacing them with Non-CAtegorical Prior (NCAP) using penultimate layer representations. (2) Pre-trained recognizers used to generate TP struggle with low-resolution images. To address this, most studies jointly train the recognizer with the STISR network to bridge the domain gap between low- and high-resolution images, but this can cause an overconfidence phenomenon in the prior modality. We highlight this issue and propose a method to mitigate it by mixing hard and soft labels. Experiments on the TextZoom dataset demonstrate an improvement by 3.5%, while our method significantly enhances generalization performance by 14.8\\% across four text recognition datasets. Our method generalizes to all TP-guided STISR networks.","url_abs":"https://arxiv.org/abs/2504.00410v1","url_pdf":"https://arxiv.org/pdf/2504.00410v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"ncap-scene-text-image-super-resolution-with","repo_url":"https://github.com/THINKWARE-AI/NCAP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"image-super-resolution","task_name":"Image Super-Resolution"},{"task_slug":"super-resolution","task_name":"Super-Resolution"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-super-resolution-on-textzoom","task":"Image Super-Resolution","dataset":"TextZoom","model":"NCAP","rank_in_archive_order":1,"of":1,"metrics":{"ASTER Overall Accuracy":"68.1","Average Accuracy":"63.7","CRNN Overall Accuracy":"58.3","MORAN Overall Accuracy":"64.6"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}