otthorn/nerf_plus_plus
1
0
Fork 0
Code Issues Pull requests Projects Releases Wiki Activity

Update README.md

Browse source
This commit is contained in:
Kai Zhang 2020-10-15 01:17:24 -04:00 committed by GitHub
parent 52ad0d2caa
commit fb9ff00b2c
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 11 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

12
README.md
View file

@ -9,8 +9,18 @@ Codebase for arXiv preprint:
* Put the data in the sub-folder data/ of this code directory. * Put the data in the sub-folder data/ of this code directory.
* Data format. * Data format.
* Each scene consists of 3 splits: train/test/validation. * Each scene consists of 3 splits: train/test/validation.
* Intrinsics and poses are stored as flattened 4x4 matrices. * Intrinsics and poses are stored as flattened 4x4 matrices; poses are camera-to-world.
* Opencv camera coordinate system is adopted, i.e., x--->right, y--->down, z--->scene. * Opencv camera coordinate system is adopted, i.e., x--->right, y--->down, z--->scene.
* To convert camera poses between Opencv and Opengl conventions, the following snippet can be used for both Opengl2Opencv and Opencv2Opengl.
```python
import numpy as np
def convert_pose(C2W):
flip_yz = np.eye(4)
flip_yz[1, 1] = -1
flip_yz[2, 2] = -1
C2W = np.matmul(C2W, flip_yz)
return C2W
```
* Scene normalization: move the average camera center to origin, and put all the camera centers inside the unit sphere. * Scene normalization: move the average camera center to origin, and put all the camera centers inside the unit sphere.
## Create environment ## Create environment