Artistic character generation technique using a controllable diffusion model

서지정보

· 발행기관 : 한국컴퓨터게임학회
· 수록지 정보 : 한국컴퓨터게임학회 논문지 / 36권 / 3호
· 저자명 : Hyemin YANG, Heekyung YANG, Kyungha MIN

목차

1. Introduction
1.2 Related Resarch
2. Body
2.1 OverView
2.2 Methode
3. Conclusion
3.1 Conclusion
3.1 compare

영어초록

With the recent advent of Metaverse, the character industry that reflects the characteristics of users' faces is drawing attention. there is a hassle that users have to select face components such as eyes, nose, and mouth one by one. In this paper, we propose a diffusion-based model that automatically generates characters from content human photographs. Our model generates user artistic characters by reflecting content information such as face angle, direction, and shape of a content human photo. In particular, our model automatically analyzes detailed information such as glasses and whiskers from content photo images and reflects them in artistic characters generated. Our network generates the final character through a three-step: diffusion process, UNet, and denoising processes. We use image encoders and CLIP encoders for the connection between style and input data. In the diffusion process, a collection of noise vectors is gradually added to a style vector to enable lossless learning of the detailed styles. All input values except for the style images are vectorized with CLIP encoders and then learned with noise style vectors in the UNet. Subsequently, noise is removed from the vectors through the UNet to obtain the artistic character image. We demonstrate our performance by comparing the results of other models with our results. Our method reflects content information without loss and generates natural high-definition characters.

참고자료

· 없음