OnomatoBridge：漫画中的拟声词翻译与渲染流水线
OnomatoBridge: Onomatopoeia Translation and Rendering Pipeline in Manga
- The University of Tokyo（东京大学）
- CyberAgent
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
提出OnomatoBridge流水线，通过过滤机制解决漫画拟声词翻译中的残留伪影与风格不一致，在Manga109数据集上显著提升英语正确性并减少日语残留。
AI中文摘要：
漫画是一种以黑白绘画绘制的漫画形式，在全球范围内日益流行。漫画中的拟声词以其独特的视觉风格特别吸引读者，这些风格传达了声音、动作和情感。视觉拟声词翻译要求将日语拟声词干净地替换为其他语言的拟声词，同时保留其视觉风格。现有方法在移除日语拟声词并渲染风格化的英语拟声词时，常常产生残留伪影或风格不一致的问题。为了解决这些问题，我们提出了OnomatoBridge，一种用于视觉拟声词翻译的过滤流水线。我们在Manga109拟声词数据集上评估了从日语到英语的OnomatoBridge，并将其与基线图像编辑模型进行了比较。实验结果表明，所提出方法过滤后的输出优于传统方法。OnomatoBridge将英语文本正确性提高了大约10到25个百分点，并将残留日语文本相对减少了约20%到50%。
英文摘要：
Manga is a comic drawn by black and white paints gaining popularity around the world. Onomatopoeia in Manga specifically appeals to the audience with its unique visual styles, which convey sound, motion, and emotion. Visual onomatopoeia translation requires the clean replacement of Japanese onomatopoeia with onomatopoeia in the other language while preserving their visual style. Existing approaches often produce residual artifacts or style inconsistency when removing the Japanese onomatopoeia and rendering stylized English onomatopoeia. To approach these problems, we present OnomatoBridge, a filtering pipeline for visual onomatopoeia translation. We evaluate OnomatoBridge from Japanese to English on the Manga109 onomatopoeia dataset and compare it with baseline image editing models. Experimental results show that the filtered outputs by the proposed method outperform those of conventional methods. OnomatoBridge improves English text correctness by roughly 10 to 25 points and reduces residual Japanese text by about 20 to 50% in relative terms.
