具有肤色感知和裸露识别功能的人像风格化框架
A Framework for Portrait Stylization with Skin-Tone Awareness and Nudity Identification
AI总结:
本研究提出一种包含裸露内容识别模块(NCIM)和肤色感知人像风格化模块(STAPSM)的框架,有效过滤有害内容并保留肤色特征,已成功实际部署。
摘要:
人像风格化是一项具有挑战性的任务,涉及将输入人像图像转换为特定风格,同时保留其固有特征。最近引入的Stable Diffusion (SD)显著提升了该领域的输出质量。然而,目前仍缺乏一个实用的风格化框架,能够有效过滤有害输入内容,并保留输入的显著特征(如肤色),同时保持风格化质量。这些挑战阻碍了此类框架的广泛部署。为了解决这些问题,本研究提出了一种人像风格化框架,其中包含裸露内容识别模块(NCIM)和肤色感知人像风格化模块(STAPSM)。在实验中,NCIM在增强显式内容过滤方面表现出良好的性能,STAPSM准确呈现了多种肤色。我们提出的框架已成功在实践中部署,并有效满足了现实世界应用的关键要求。
英文摘要:
Portrait stylization is a challenging task involving the transformation of an input portrait image into a specific style while preserving its inherent characteristics. The recent introduction of Stable Diffusion (SD) has significantly improved the quality of outcomes in this field. However, a practical stylization framework that can effectively filter harmful input content and preserve the distinct characteristics of an input, such as skin-tone, while maintaining the quality of stylization remains lacking. These challenges have hindered the wide deployment of such a framework. To address these issues, this study proposes a portrait stylization framework that incorporates a nudity content identification module (NCIM) and a skin-tone-aware portrait stylization module (STAPSM). In experiments, NCIM showed good performance in enhancing explicit content filtering, and STAPSM accurately represented a diverse range of skin tones. Our proposed framework has been successfully deployed in practice, and it has effectively satisfied critical requirements of real-world applications.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。