A Large-scale Dataset for Robust Complex Anime Scene Text Detection

ICLR 2026 Conference Submission8866 Authors

Keywords: Text Detection, Dataset, Anime

Abstract: Current text detection datasets primarily target natural or document scenes, where text typically appear in regular font and shapes, monotonous colors, and orderly layouts. The text usually arranged along straight or curved lines. However, these characteristics differ significantly from anime scenes, where text is often diverse in style, irregularly arranged, and easily confused with complex visual elements such as symbols and decorative patterns. Text in anime scene also includes a large number of handwritten and stylized fonts. Motivated by this gap, we introduce \textit{AnimeText}, a large-scale dataset containing 735K images and 4.2M annotated text blocks. It features hierarchical annotations and hard negative samples tailored for anime scenarios. To evaluate the robustness of \textit{AnimeText} in complex anime scenes, we conducted cross-dataset benchmarking using state-of-the-art text detection methods. Experimental results demonstrate that models trained on \textit{AnimeText} outperform those trained on existing datasets in anime scene text detection tasks.

Primary Area: datasets and benchmarks

Submission Number: 8866