HAT Super-Resolution and a PARSeq+CLIP4STR Voting Ensemble for Extreme In-the-Wild License Plate Recognition
Not on the map. Why?
Abstract (arXiv)
We describe our entry to the ICIP 2026 Grand Challenge on Extreme In-the-Wild License Plate Super-Resolution (XLPSR), which scored 9.73 wECR on the public validation leaderboard. The system pairs a Hybrid Attention Transformer super-resolution (HAT) front-end with an ensemble of two scene-text recognisers (PARSeq-S and CLIP4STR-B) and a confidence-weighted character-voting scheme that abstains on uncertain positions. We treat XLPSR as a recognition task gated by image legibility: the SR step exists to lift characters out of sub-pixel territory, and the asymmetric scoring rule (+2 / -1 / 0) is exploited explicitly through abstention. Our pipeline runs in 1.7 s per sequence on RTX 3090 (max 2.7 s, p99 2.4 s), well under the 60 s/sequence Docker budget.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 6 of its 6 references that are in the map. First posted on arXiv 9 Jul 2026.
Builds on
6 of 6 references.
References · 6
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
- 2021Designing a Practical Degradation Model for Deep Blind Image Super-Resolutioncited by 524
- 2022Activating More Pixels in Image Super-Resolution Transformercited by 433
- 2022Scene Text Recognition with Permuted Autoregressive Sequence Modelscited by 148
- 2023CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Modelcited by 30
- 2021SwiftSRGAN -- Rethinking Super-Resolution for Efficient and Real-time Inferencecited by 4
Built on by
Not cited yet.