Journal of Broadcast Engineering (방송공학회논문지)

The Korean Institute of Broadcast and Media Engineers (한국방송∙미디어공학회)
권호 표지
DOI QR코드

DOI QR Code

Dynamic Reconstruction Algorithm of 3D Volumetric Models

3D 볼류메트릭 모델의 동적 복원 알고리즘

  • Park, Byung-Seo (Kwangwoon university Electronic Materials Engineering) ;
  • Kim, Dong-Wook (Kwangwoon university Electronic Materials Engineering) ;
  • Seo, Young-Ho (Kwangwoon university Electronic Materials Engineering)
  • 박병서 (광운대학교 전자재료공학과) ;
  • 김동욱 (광운대학교 전자재료공학과) ;
  • 서영호 (광운대학교 전자재료공학과)
  • Received : 2022.01.24
  • Accepted : 2022.02.28
  • Published : 2022.03.30
Download PDF
⟨ Previous Next ⟩

Abstract

The latest volumetric technology's high geometrical accuracy and realism ensure a high degree of correspondence between the real object and the captured 3D model. Nevertheless, since the 3D model obtained in this way constitutes a sequence as a completely independent 3D model between frames, the consistency of the model surface structure (geometry) is not guaranteed for every frame, and the density of vertices is very high. It can be seen that the interconnection node (Edge) becomes very complicated. 3D models created using this technology are inherently different from models created in movie or video game production pipelines and are not suitable for direct use in applications such as real-time rendering, animation and simulation, and compression. In contrast, our method achieves consistency in the quality of the volumetric 3D model sequence by linking re-meshing, which ensures high consistency of the 3D model surface structure between frames and the gradual deformation and texture transfer through correspondence and matching of non-rigid surfaces. And It maintains the consistency of volumetric 3D model sequence quality and provides post-processing automation.

최신 볼류메트릭 기술이 제공하는 높은 기하학적 정확도와 사실성은 실제 객체와 캡춰된 3D 모델 간 높은 일치도를 보장한다. 그럼에도 불구하고 이렇게 획득된 3D 모델은 프레임 간 완전히 독립적인 3D모델로 시퀀스를 구성하고 있다는 측면에서, 매 프레임 모델 표면 구조(Geometry)의 일관성이 보장 되지 않으며, 정점(Vertex)의 밀도가 매우 높고 정점 간 연결 노드(Edge)가 매우 복잡해지는 특징을 확인 할 수 있다. 이 기술을 통해 생성된 3D 모델은 영화나 비디오 게임 제작 파이프라인에서 제작된 모델과는 본질적으로 다르며, 실시간 렌더링, 애니메이션 및 시뮬레이션, 압축과 같은 응용 분야에서 직접 사용하기에 적합하지 않다. 이와는 대조적으로 우리의 방법은 프레임 간 3D 모델 표면 구조의 높은 일관성을 확보하는 리메싱(Remeshing)과 비강체 표면(Non-rigid Shape)의 대응(Correspondences) 및 매칭(Matching)을 통한 점진적 변형(Deformation) 과정 및 텍스쳐 전달(Texture Transfer) 과정을 연결함으로서 볼류메트릭 3D 모델 시퀀스 품질의 일관성을 유지하며, 후 처리 과정의 자동화를 제공한다.

Keywords

Acknowledgement

This research was supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education in 2022 (NRF-2018R1D1A1B07043220).

References

  1. R. Newcombe et al., "KinectFusion: Real-Time Dense Surface Mapping and Tracking," in IEEE International Symposium on Mixed and Augmented Reality(ISMAR), pp.127-136. 2014. doi: https://doi.org/10.1109/ISMAR.2011.6092378.
  2. K. Guo, F. Xu, T. Yu, X. Liu, Q. Dai and Y. Liu, "Real-Time Geometry, Albedo, and Motion Reconstrution using a Single RGB-D Camera," in ACM Trans. on Graphics(ToG), Vol.36, No.4, Article 44a (August 2017). doi: https://doi.org/10.1145/3072959.3083722
  3. R. Newcombe et al., "DynamicFusion: Reconstruction and tracking of non-rigid scenes in real-time," in IEEE Computer Vision and Pattern Recognition (CVPR), pp.343-352, 2015. doi: https://doi.org/10.1109/cvpr.2015.7298631
  4. P. Alliez et al., "Recent advances in remeshing of surfaces," in Springer ,Berlin, Heidelberg, pp. 53-82, 2008. doi: https://doi.org/10.1007/978-3- 540-33265-7_2
  5. P. Alliez et al., "Isotropic surface remeshing," in Proc. Shape Model. Int., pp. 49-58, 2003. doi: https://doi.org/10.1109/SMI.2003.1199601.
  6. J. Shewchuk, "What is a good linear element? interpolation, onditioning, and quality measures," in Proc. 11th Int. Meshing Roundtable, pp. 115-126, 2002. http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.19.2164
  7. Y. Wang et al., "Isotropic Surface Remeshing without Large and Small Angles," in IEEE Transactions on Visualization and Computer Graphics, vol. 25, no. 7, pp. 2430-2442. doi: https://doi.org/10.1109/ TVCG.2018.2837115.
  8. S. Melzi et al.,"Intrinsic/extrinsic embedding for functional remeshing of 3D shapes", Computers & Graphics, Vol 88, pp. 1-12, 2020. doi: https://doi.org/10.1016/j.cag.2020.02.002.
  9. Y. Sahillioglu and Y. Yemez. "Coarse-to-fine combinatorial matching for dense isometric shape correspondence", Computer Graphics Forum. Vol. 30, No. 5, pp. 1461-1470, 2011. doi: https://doi.org/10.1111/ j.1467-8659.2011.02020.x
  10. Y. Lipman and T. Funkhouser. "Mobius voting for surface correspondence." ACM Trans. Graph. Vol. 28, No.3, 2009. doi: https:// doi.org/10.1145/1531326.1531378.
  11. M. Ovsjanikov, M. Ben-Chen, J. Solomon, A. Butscher, and L. Guibas. "Functional maps: A flexible representation of maps between shapes." ACM Transactions on Graphics, Vol.31, No.4, pp. 1-11, 2012. doi: https://doi.org/10.1145/2185520.2185526
  12. R. Kimmel and J. Sethian, "Minimal discrete curves and surfaces," in Proc. Nat. Academy Sci, vol. 95, pp. 8431-8435, 1998. doi: https://dl.acm.org/doi/10.5555/1086970
  13. X. Ying, X. Wang, and Y. He, "Saddle vertex graph (SVG): A novel solution to the discrete geodesic problem," ACM Trans. Graph., Vol. 32, No. 6, pp. 170:1-170:12, 2013. doi: https://doi.org/10.1145/2508363.2508379
  14. K. Crane, F. de Goes, M. Desbrun, and P. Schroder, "Digital geometry processing with discrete exterior calculus," in Proc. ACM SIGGRAPH 2013 Courses, pp. 7:1-7:126, 2013. doi: https://doi.org/10.1145/2504435. 2504442.
  15. Sahillioglu, Yusuf. "A genetic isometric shape correspondence algorithm with adaptive sampling." ACM Transactions on Graphics (TOG), Vol. 37. No.5, pp. 1-14, 2018. doi: https://doi.org/10.1145/ 3243593
  16. Sumner, Robert W., and Jovan Popovic. "Deformation transfer for triangle meshes." ACM Transactions on graphics (TOG), Vol. 23, No.3, pp.399-405. 2004. doi: https://doi.org/10.1145/1015706.1015736
  17. http://www.cloudcompare.org/, Dec. 2016.
  18. http://tosca.cs.technion.ac.il/book/resources_data.html, November. 2010.
  19. X. Ge, "Non-rigid registration of 3D point clouds under isometric deformation", ISPRS Journal of Photogrammetry and Remote Sensing, vol. 121, pp. 192-202, 2016. doi: https://doi.org/10.1016/j.isprsjprs.2016. 09.009
  20. M. Marinov, L. Kobbelt, "Optimization methods for scattered data approximation with subdivision surfaces", Graphical Models, vol. 67, pp. 452-473, 2015. doi: https://doi.org/10.1016/j.gmod.2005.01.003
  21. V. Estellers, F. Schmidt and D. Cremers, "Robust Fitting of Subdivision Surfaces for Smooth Shape Analysis," 2018 International Conference on 3D Vision (3DV), 2018, pp. 277-285. doi: 10.1109/3DV.2018.00040