|Title:||SegAnimeChara: Segmenting Anime Characters Generated by AI||Authors:||Tseng, Andy Yu Hsiang
Wang, Wen Fan
|Keywords:||Anime | Body Segmentation | Character Segmentation | Design | Game | Manga | Otaku | Pose Segmentation | Semantic Segmentation||Issue Date:||23-Jul-2023||Start page/Pages:||1-2||Source:||Proceedings - SIGGRAPH 2023 Posters||Abstract:||
This work introduces SegAnimeChara, a novel system of transforming AI-generated anime images into game characters while retaining unique features. Using volume-based body pose segmentation, SegAnimeChara can efficiently, zero-shot, segment body parts from generative images based on OpenPose human skeleton. Furthermore, this system integrates a semantic segmentation pipeline based on the text prompts of the existing Text2Image workflow. The system conserves the game character's unique outfit and reduces the redundant duplicate text prompts for semantic segmentation.
Special Interest Group on Computer Graphics and Interactive Techniques Conference - Posters, SIGGRAPH 2023, Los Angeles, 6 August 2023 - 10 August 2023
|Appears in Collections:||資訊管理學系|
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.