# 计图开源：神经辐射场的几何编辑方法NeRF-Editing

2022/08/04

## 计图开源：神经辐射场的几何编辑方法NeRF-Editing

Part1

Part2

1. 构建四面体网格(离散的体表示)来覆盖提取的三角形网格。在三角网格表面沿法线方向偏移一定距离，来得到一个包裹它的笼状网格。空间中的离散体表示可以通过对该笼状网格四面体化得到。
2. 将面网格变形转换为空间体网格变形。利用三角形网格顶点的位移来驱动四面体网格的变形，得到变形后的四面体网格T'。分别记变形前后四面体网格的顶点为t'，该变形可通过如下的公式，优化ARAP能量式求解，其中是三角形网格的重心坐标权值构成的矩阵，该问题可以通过拉格朗日乘子法转化为线性方程组求解。

Part3

• 第一种是在弯曲光线时，直接选用最近邻的网格顶点位移作为该采样点的位移，记为“Closest Point”；
• 第二种选取了采样点最近邻的三个网格顶点，以距离的倒数作为系数线性插值得到位移，记为“3NN”。

https://github.com/IGLICT/NeRF-Editing

1. Yu-Jie Yuan#, Yang-Tian Sun#, Yu-Kun Lai, Yuewen Ma, Rongfei Jia, Lin Gao, NeRF-Editing: Geometry editing of neural radiance fields, IEEE CVPR, 2022, 18353-18364.
2. Ben Mildenhall, Pratul P Srinivasan, Matthew Tancik, Jonathan T Barron, Ravi Ramamoorthi, and Ren Ng, NeRF: Representing scenes as neural radiance fields for view synthesis, ECCV, 2020, 405-421.

3. Shu-Yu Chen, Lin Gao, Yu-Kun Lai, and Shihong Xia, Rigidity controllable as-rigid-as-possible shape deformation, Graphical Models, 2017, Vol. 91, 13-21.

4. Lin Gao, Yu-Kun Lai, Jie Yang, Zhang Ling-Xiao, Shihong Xia, and Leif Kobbelt, Sparse data driven mesh deformation, IEEE Transactions on Visualization and Computer Graphics, 2021, Vol. 27, No. 3, 2085-2100.

5. Steven Liu, Xiuming Zhang, Zhoutong Zhang, Richard Zhang, Jun-Yan Zhu, and Bryan Russell, Editing conditional radiance fields, IEEE ICCV, 2021, 5773-5783.

6. Peng Wang, Lingjie Liu, Yuan Liu, Christian Theobalt, TakuKomura, and Wenping Wang, NeuS: Learning neural implicit surfaces by volume rendering for multi-view reconstruction, NeurIPS, 2021.

7. Olga Sorkine-Hornung and Marc Alexa, As-rigid-as-possible surface modeling, Symposium on Geometry Processing, 2007.

8. Yixin Hu, Teseo Schneider, Bolun Wang, Denis Zorin, and Daniele Panozzo, Fast tetrahedral meshing in the wild, ACM TOG, 2020, 39:117:1-117:18.

GGC往期回顾

5. CVMJ获得首个SCI影响因子4.127，进入Q1区