Earticle

초록

영어

This study proposes a mobile-based lightweight deep learning model (Lite-MCC) capable of reconstructing three-dimensional (3D) spatial structures from a single RGB image. Conventional 3D reconstruction models require multi-view inputs or point cloud data and depend on large-scale computational resources, which limits their real-time applicability in practical environments. To address this limitation, the proposed Lite-MCC model simplifies the existing Multiview Compressive Coding (MCC) architecture, enabling accurate 3D reconstruction using only a single image. The model adopts a parallel structure consisting of a Vision Transformer (ViT-Tiny) and a Geometry Encoder to extract visual and spatial features simultaneously, while a Transformer Decoder generates the corresponding 3D point cloud. Furthermore, depth map–based input transformation and ONNX-based optimization are employed to achieve efficient real-time inference on edge devices. Experimental results on the CO3D dataset demonstrate that Lite-MCC reduces computational cost by 87% and memory usage by 65%, while maintaining a Chamfer Distance of 0.045, comparable to the original MCC model. These results indicate that the proposed method provides a promising direction for lightweight AI models enabling low-cost, real-time 3D recording and visualization.

목차

ABSTRACT
1. 서론
2. 관련 연구
2.1 기존 3D Reconstruction 방법론
2.2 MCC(Multiview Compressive Coding) 기반 모델
2.3 모델 경량화 및 모바일 최적화
3. 제안하는 방법
3.1 전체 구조 개요
3.2 경량화 전략
3.3 학습 데이터셋 및 손실 함수
4. 실험 및 결과
5. 논의 및 연구
Acknowledgement
참고문헌

키워드

저자

• Seung min Jung [ 정승민 | Department of AI & Informatics, Graduate School, Sangmyung University ]
• Byeong Seon An [ 안병선 | Department of AI & Informatics, Graduate School, Sangmyung University ]
• Song hee Park [ 박송희 | Department of AI & Informatics, Graduate School, Sangmyung University ]
• Hak jin Lee [ 이학진 | Department of AI & Informatics, Graduate School, Sangmyung University ]
• Ji woo Lee [ 이지우 | Digital Analysis Division, National Forensic Service ]
• Nam In Park [ 박남인 | Digital Analysis Division, National Forensic Service ] Corresponding Author
• Eui Chul Lee [ 이의철 | Department of Human-Centered Artificial Intelligence, Sangmyung University ] 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