“SegAnimeChara: Segmenting Anime Characters Generated by AI” by Tseng, Wang and Chen
Conference:
Type(s):
Entry Number: 35
Title:
- SegAnimeChara: Segmenting Anime Characters Generated by AI
Session/Category Title: Posters: Image, Video, & Computer Vision
Presenter(s)/Author(s):
Abstract:
This work introduces SegAnimeChara, a novel system of transforming AI-generated anime images into game characters while retaining unique features. SegAnimeChara can efficiently, zero-shot, segment anime body parts from generative images. Furthermore, the system conserves the game character’s unique outfit and reduces the redundant duplicate text prompts in semantic segmentation.
ACM Digital Library Publication:
Overview Page:
Submit a story:
If you would like to submit a story about this presentation, please contact us: historyarchives@siggraph.org
