{"ID":2844525,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.05818","arxiv_id":"2511.05818","title":"LRANet++: Low-Rank Approximation Network for Accurate and Efficient Text Spotting","abstract":"End-to-end text spotting aims to jointly optimize text detection and recognition within a unified framework. Despite significant progress, designing an accurate and efficient end-to-end text spotter for arbitrary-shaped text remains challenging. We identify the primary bottleneck as the lack of a reliable and efficient text detection method. To address this, we propose a novel parameterized text shape representation based on low-rank approximation for precise detection and a triple assignment detection head for fast inference. Specifically, unlike current data-irrelevant shape representation methods, we exploit shape correlations among labeled text boundaries to construct a robust low-rank subspace. By minimizing an $\\ell_1$-norm objective, we extract orthogonal vectors that capture the intrinsic text shape from noisy annotations, enabling precise reconstruction via the linear combination of only a few basis vectors. Next, the triple assignment scheme decouples training complexity from inference speed. It utilizes a deep sparse branch to guide an ultra-lightweight inference branch, while a dense branch provides rich parallel supervision. Building upon these advancements, we integrate the enhanced detection module with a lightweight recognition branch to form an end-to-end text spotting framework, termed LRANet++, capable of accurately and efficiently spotting arbitrary-shaped text. Extensive experiments on challenging benchmarks demonstrate the superiority of LRANet++ compared to state-of-the-art methods. Code is available at: https://github.com/ychensu/LRANet-PP.","short_abstract":"End-to-end text spotting aims to jointly optimize text detection and recognition within a unified framework. Despite significant progress, designing an accurate and efficient end-to-end text spotter for arbitrary-shaped text remains challenging. We identify the primary bottleneck as the lack of a reliable and efficient...","url_abs":"https://arxiv.org/abs/2511.05818","url_pdf":"https://arxiv.org/pdf/2511.05818v2","authors":"[\"Yuchen Su\",\"Zhineng Chen\",\"Yongkun Du\",\"Zuxuan Wu\",\"Hongtao Xie\",\"Yu-Gang Jiang\"]","published":"2025-11-08T03:08:03Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":607300,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2844525,"paper_url":"https://arxiv.org/abs/2511.05818","paper_title":"LRANet++: Low-Rank Approximation Network for Accurate and Efficient Text Spotting","repo_url":"https://github.com/ychensu/LRANet-PP","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}