논문 상세보기

반응-확산 모델 기반의 연속적인 톤의 표현 KCI 등재

Continuous Tone Representation based Reaction-Diffusion Model

  • 언어KOR
  • URLhttps://db.koreascholar.com/Article/Detail/338315
구독 기관 인증 시 무료 이용이 가능합니다. 4,000원
한국컴퓨터게임학회 논문지 (Journal of The Korean Society for Computer Game)
한국컴퓨터게임학회 (Korean Society for Computer Game)
초록

In this paper, we proposed novel continuous tone representational method based reaction-diffusion model. We extended previous related research of hedcut-style rendering by adding controllability to reaction-diffusion based texture generation method. These controls includes pattern size and pattern direction for various style rendering. Our method is comparable with stipping method which can generate artistic style rendering with continuous tone representation of input images. While stippling can show stable tonal results for low density points area, high density region which stipples redundant is suffer from non-linear brightness. On the contrary, our method shows stable tonal results for all brightness spans. We also present anisotropic diffusion for directional pattern generation which can applied to more various style rendering. In this contribution includes mathematical model and results of various style.

목차
ABSTRACT
 1. 서론
 2. 연구 배경
  2.1 반응-확산 모델
  2.2 비사실적 렌더링
 3. 제안된 방법
  3.1 연속된 톤의 표현
  3.2 패턴의 크기와 방향의 제어
 4. 실험 결과
  4.1 점묘법과 비교
  4.2 패턴 크기의 제어
  4.3 등방확산과 비등방 확산
 5. 결론
 참고문헌
저자
  • 조청운(Division of Digital Contents, Im Kwon Taek College of Film and Media Arts, Dongseo University) | Cheung Woon Jho Correspondence to