Papers › NCAP: Scene Text Image Super-Resolution with Non-CAtegorical Prior

NCAP: Scene Text Image Super-Resolution with Non-CAtegorical Prior

1 Apr 2025arXiv:2504.00410archive 2025-07-28

Dongwoo Park, Suk Pil Ko

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.

PaperPDFCode

Code

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image Super-ResolutionSuper-Resolution

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Super-Resolution TextZoom NCAP ASTER Overall Accuracy 68.1 #1 of 1 Archive leaderboard report
Image Super-Resolution TextZoom NCAP Average Accuracy 63.7 #1 of 1 Archive leaderboard report
Image Super-Resolution TextZoom NCAP CRNN Overall Accuracy 58.3 #1 of 1 Archive leaderboard report
Image Super-Resolution TextZoom NCAP MORAN Overall Accuracy 64.6 #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections