지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 자료유형
- 학술저널
- 저자정보
- 발행연도
- 2024.12
- 수록면
- 1,147 - 1,156 (10page)
- DOI
- 10.5909/JBE.2024.29.7.1147
이용수
초록· 키워드
오류제보하기
The MPEG INVR (Implicit Neural Visual Representation) Ad-hoc Group (AhG) is exploring potential standard technologies for efficient representation and compression of 3D spatial videos using the explicit representation model of 3DGS (3D Gaussian Splatting). This paper presents a compaction method for the Spacetime Gaussian (STG) model, which extends 3D Gaussians into 4D spacetime domain. The proposed method applies a KNN algorithm spatiotemporally to prune STGs. During this process, the pruning ratio is adaptively adjusted based on the rendering quality loss to prevent excessive pruning and to maintain rendering quality. Experimental results show that the proposed method demonstrates improved compaction performance compared to the existing STG model in 6DoF video rendering, reducing the model size by 54% compared to the conventional STG model, with only a 0.2 dB reduction in visual quality.
목차
Abstract
Ⅰ. Introduction
Ⅱ. 3DGS and STG
Ⅲ. STG compaction using KNN algorithm
Ⅳ. Experimental results
Ⅴ. Conclusion
References
참고문헌 (9)
참고문헌 신청
V. Sitzmann, J. N. P. Martel, A. W. Bergman, D. B. Lindell, and G. Wetzstein, “Implicit neural representations with periodic activation functions,” Advances in Neural Information Processing Systems, vol. 13, pp.7462–7473, 2020. doi: https://doi.org/10.48550/arXiv.2006.09661
B. Mildenhal, P. P. Srinivasan, M. Tancik, J. T. Barron, R. Ramamoorthi, and R. Ng, “Nerf: Representing Scenes as Neural Radiance Fields for View Synthesis,” Proceedings of the European Conference on Computer Vision, pp. 405-421, Aug. 2020. doi: https://doi.org/10.1007/978-3-030-58452-8_24
S. Fridovich-Keil, A. Yu, M. Tancik, Q. Chen, B. Recht, and A. Kanazawa, “Plenoxels: Radiance Fields without Neural Networks,” Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5501–5510, 2022. doi: https://doi.org/10.1109/CVPR52688.2022.00542
B. Kerbl, G. Kopanas, T. Leimkühler, and G. Drettakis, “3D Gaussian Splatting for Real-Time Radiance Field Rendering,” ACM Transactions on Graphics, vol.42, No.4, pp.1–14, 2023. doi: https://doi.org/10.1145/3592433
Guanjun Wu, Taoran Yi, Jiemin Fang, Lingxi Xie, Xiaopeng Zhang, Wei Wei, Wenyu Liu, Qi Tian and Xinggang Wang, “4D Gaussian Splatting for Real-Time Dynamic Scene Rendering,” arXiv preprint arXiv:2310.08528, 2023. doi: https://doi.org/10.48550/arXiv.2310.08528
B. Mildenhal, P. P. Srinivasan, M. Tancik, J. T. Barron, R. Ramamoorthi, and R. Ng, “Nerf: Representing Scenes as Neural Radiance Fields for View Synthesis,” Proceedings of the European Conference on Computer Vision, pp. 405-421, Aug. 2020. doi: https://doi.org/10.1007/978-3-030-58452-8_24
S. Fridovich-Keil, A. Yu, M. Tancik, Q. Chen, B. Recht, and A. Kanazawa, “Plenoxels: Radiance Fields without Neural Networks,” Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5501–5510, 2022. doi: https://doi.org/10.1109/CVPR52688.2022.00542
B. Kerbl, G. Kopanas, T. Leimkühler, and G. Drettakis, “3D Gaussian Splatting for Real-Time Radiance Field Rendering,” ACM Transactions on Graphics, vol.42, No.4, pp.1–14, 2023. doi: https://doi.org/10.1145/3592433
Guanjun Wu, Taoran Yi, Jiemin Fang, Lingxi Xie, Xiaopeng Zhang, Wei Wei, Wenyu Liu, Qi Tian and Xinggang Wang, “4D Gaussian Splatting for Real-Time Dynamic Scene Rendering,” arXiv preprint arXiv:2310.08528, 2023. doi: https://doi.org/10.48550/arXiv.2310.08528
이 논문과 함께 이용한 논문
양자화 및 동영상 코덱을 활용한 4D Gaussian Splatting 압축 기법
최재열
,
김영규
,
정종범
외 2명
한국방송미디어공학회 학술발표대회 논문집
2024
.06
동적 이미지 합성을 위한 4D Gaussian Splatting 기법 비교 및 연구 동향
우민수
,
진인환
,
김준수
외 2명
방송공학회논문지
2025
.01
깊이 정보와 3DGS 기반 가상 시점 영상 생성에서 노말 정보의 적용 방법
임한신
,
김현철
,
추현곤
한국방송미디어공학회 학술발표대회 논문집
2024
.11
NeRF(Neural Radiance Fields) 상용화가 3D 애니메이션 산업에 가져올 제작 패러다임 변화 연구
이순주
,
김지윤
애니메이션연구
2024
.09
최근 본 자료
댓글(0)
0
UCI(KEPA) : I410-151-25-02-091243729