Papers › TPS++: Attention-Enhanced Thin-Plate Spline for Scene Text Recognition

TPS++: Attention-Enhanced Thin-Plate Spline for Scene Text Recognition

9 May 2023arXiv:2305.05322archive 2025-07-28

Tianlun Zheng, Zhineng Chen, Jinfeng Bai, Hongtao Xie, Yu-Gang Jiang

Text irregularities pose significant challenges to scene text recognizers. Thin-Plate Spline (TPS)-based rectification is widely regarded as an effective means to deal with them. Currently, the calculation of TPS transformation parameters purely depends on the quality of regressed text borders. It ignores the text content and often leads to unsatisfactory rectified results for severely distorted text. In this work, we introduce TPS++, an attention-enhanced TPS transformation that incorporates the attention mechanism to text rectification for the first time. TPS++ formulates the parameter calculation as a joint process of foreground control point regression and content-based attention score estimation, which is computed by a dedicated designed gated-attention block. TPS++ builds a more flexible content-aware rectifier, generating a natural text correction that is easier to read by the subsequent recognizer. Moreover, TPS++ shares the feature backbone with the recognizer in part and implements the rectification at feature-level rather than image-level, incurring only a small overhead in terms of parameters and inference time. Experiments on public benchmarks show that TPS++ consistently improves the recognition and achieves state-of-the-art accuracy. Meanwhile, it generalizes well on different backbones and recognizers. Code is at https://github.com/simplify23/TPS_PP.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

simplify23/tps_pp officialmentioned in papermentioned on GitHubpytorch report

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

Optical Character Recognition (OCR)Scene Text Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Scene Text Recognition CUTE80 NRTR+TPS++ Accuracy 92.4 #16 of 18 Archive leaderboard report
Scene Text Recognition IC13 ABINet-LV+TPS++ Accuracy 97.8 #1 of 1 Archive leaderboard report
Scene Text Recognition SVT NRTR+TPS++ Accuracy 94.6 #17 of 37 Archive leaderboard report
Scene Text Recognition SVT-P ABINet-LV+TPS++ Accuracy 89.6 #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.

Methods

Content-based Attention

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