상세정보
학술대회
Generating Face Images Using VQGAN and Sparse Transformer
- 발행일
- 202110
- 출처
- International Conference on Information and Communication Technology Convergence (ICTC) 2021, pp.1642-1644
- 협약과제
- 21IH3500, 교육콘텐츠에 대한 인공지능 기반 저작권 침해 의심요소 검출 및 대체 공유저작물 추천기술 개발, 서용석
- 초록
- In this paper, we present a system for face image generation using VQGAN and sparse transformer. We explore the use of VQGAN models to learn visual tokens of image constituents and enhance the autoregressive priors to generate synthetic samples. We demonstrate that the routing transformer which learns sparse attention patterns over the visual tokens can generate samples with high-quality on face image datasets such as FFHQ and CelebA-HQ, while not suffering from mode collapse and lack of diversity.
- KSP 제안 키워드
- Face Image, High-quality, Image datasets, Image generation