Earticle

초록

영어

Recent advances in 3D data-driven digital twin research have revealed limitations in existing tree reconstruction methods, which rely solely on either scanning or procedural generation. To address this issue, this study proposes a hybrid pipeline that integrates data-driven reconstruction and procedural generation using Gaussian Splatting(GS) data. The proposed method converts multi-view GS outputs into dense point clouds and extracts a stable skeletal structure through color-density-based graph analysis. Fine branches and leaves are procedurally generated using a space colonization algorithm that incorporates botanical principles, achieving a natural and structurally coherent form. Quantitative evaluations using Chamfer distance and Intersection-over-Union metrics demonstrate high geometric similarity and volumetric consistency with the original GS data. The proposed GS-based hybrid framework ensures both visual realism and biological plausibility, enabling efficient and reliable digital twin tree modeling.

목차

ABSTRACT
1. 연구의 필요성 및 목적
2. 연구 방법 및 범위
3. 이론적 배경
3.1 Gaussian Splatting 및 포인트 클라우드 변환
3.2 관련연구
3.3 3D 나무 모델링을 위한 식생학적 원리
4. GS 데이터 기반의 절차적 나무 에셋 생성 파이프라인
4.1 포인트 클라우드 데이터 정제 (Preprocessing)
4.2 주요 가지 재구성 (Scaffold Branch Reconstruction)
4.3 세부 가지 생성 (Lateral Branch Generation)
4.4 메시화 (Meshing)
4.5 잎 배치 (Leaf Placement)
5. 연구결과
5.1 전체 형태 및 구조적 충실도
5.2 표면 근접도 정밀 분석
6. 결론
Acknowledgement
참고문헌

키워드

저자

• Seung-Woo Jeong [ Master’s Course, Department of Entertainment Technology, Graduate School of Advanced Imaging Science, Multimedia and Film, Chung-Ang University, Seoul 06911, Korea ]
• Tae-Kyung Yoo [ Professor, College of Art & Technology, Chung-Ang University, Anseong 17546, Korea ] Corresponding Author

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  컴퓨터게임및콘텐츠논문지(구 한국컴퓨터게임학회논문지) [Journal of Computer Games and Contents]

• 간기

  월간

• pISSN

  3091-7409

• eISSN

  3092-3638

• 수록기간

  2002~2026

• 등재여부

  KCI 등재

• 십진분류

  KDC 691 DDC 793