三维场景表示的体渲染增强与冗余约束分析

何 金旭
重庆交通大学信息科学与工程学院

摘要


三维高斯泼溅（3DGS）在复杂场景中易产生伪影和细节缺失。为提升重建质量，本文在早期3DGS框架中
引入体渲染计算，使高斯贡献沿光线连续累积以减轻无序带来的误差；并结合透射率裁剪剔除冗余椭球，同时加入
多视角一致性约束提高几何稳定性。实验结果显示，该方法可在多类数据集上有效减少噪声、提升颜色与深度图的
可靠性，具有一定工程应用价值。

关键词


三维重建；高斯泼溅；体渲染；多视图一致性；高斯裁剪

全文:

PDF


参考


[1]Kerbl B, Kopanas G, Leimkühler T, et al. 3d

gaussian splatting for real-time radiance field rendering[J].

ACM Trans. Graph., 2023, 42(4): 139:1-139:14.

[2]Bakurov I, Buzzelli M, Schettini R, et al. Structural

similarity index (SSIM) revisited: A data-driven approach[J].

Expert Systems with Applications, 2022, 189: 116087.

[3]Hedman P, Philip J, Price T, et al. Deep blending for

free-viewpoint image-based rendering[J]. ACM Transactions

on Graphics (ToG), 2018, 37(6): 1-15.

[4]Wang P, Liu L, Liu Y, et al. Neus: Learning neural

implicit surfaces by volume rendering for multi-view

reconstruction[C]//Proceedings of the 35th International

Conference on Neural Information Processing Systems. Red

Hook: ACM, 2021: 2081-2094.

[5]Yariv L, Gu J, Kasten Y, et al. Volume rendering of

neural implicit surfaces[J]. Advances in Neural Information

Processing Systems, 2021, 34: 4805-4815.

[6]Huang B, Yu Z, Chen A, et al. 2d gaussian splatting for

geometrically accurate radiance fields[C]//ACM SIGGRAPH

2024 conference papers. Colorado: ACM, 2024: 1-11.

[7]Yu Z, Sattler T, Geiger A. Gaussian opacity fields:

Efficient adaptive surface reconstruction in unbounded

scenes[J]. ACM Transactions on Graphics (TOG), 2024,

43(6): 1-13.

[8]Barron J T, Mildenhall B, Verbin D, et al. Mipnerf 360: Unbounded anti-aliased neural radiance fields[C]//

Proceedings of the IEEE/CVF conference on computer vision

and pattern recognition. New Orleans: IEEE Press, 2022:

5470-5479.


Refbacks

  • 当前没有refback。