Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kim, Seungkwon, Kim, Sangyeon, Nam, Seung-Hun
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2403.14264
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866907838522064896
author Kim, Seungkwon
Kim, Sangyeon
Nam, Seung-Hun
author_facet Kim, Seungkwon
Kim, Sangyeon
Nam, Seung-Hun
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2403_14264
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Framework for Portrait Stylization with Skin-Tone Awareness and Nudity Identification
Kim, Seungkwon
Kim, Sangyeon
Nam, Seung-Hun
Computer Vision and Pattern Recognition
Artificial Intelligence
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.
title A Framework for Portrait Stylization with Skin-Tone Awareness and Nudity Identification
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2403.14264