HAT Super-Resolution and a PARSeq+CLIP4STR Voting Ensemble for Extreme In-the-Wild License Plate Recognition

A team submitted a Hybrid Attention Transformer super-resolution front-end paired with a PARSeq+CLIP4STR voting ensemble to the ICIP 2026 Grand Challenge on Extreme In-the-Wild License Plate Super-Resolution, achieving a 9.73 wECR on the public validation leaderboard. The system runs in under 3 seconds per sequence on an RTX 3090, well within the competition's 60-second budget.

arXiv:2607.08896v1 Announce Type: new Abstract: 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.