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 2020-10-21 09:46:20 -04:00 committed by GitHub
parent 4329374c22
commit f157f11976
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 4 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

8
README.md
View file

@ -58,12 +58,12 @@ Plese cite our work if you use the code.
} }
``` ```
## Generate poses with [COLMAP SfM](https://colmap.github.io/) ## Generate camera parameters (intrinsics and poses) with [COLMAP SfM](https://colmap.github.io/)
You can use the scripts inside *'colmap_runner/'* to generate camera poses from images with COLMAP SfM. You can use the scripts inside *'colmap_runner/'* to generate camera parameters from images with COLMAP SfM.
* Specify *'img_dir'* and *'out_dir'* in *'colmap_runner/run_colmap.py'*. * Specify *'img_dir'* and *'out_dir'* in *'colmap_runner/run_colmap.py'*.
* Inside *'colmap_runner/'*, execute command *'python run_colmap.py'*. * Inside *'colmap_runner/'*, execute command *'python run_colmap.py'*.
* After program finishes running, you would see the posed images in the folder *'out_dir/posed_images'*. * After program finishes, you would see the posed images in the folder *'out_dir/posed_images'*.
* Distortion-free images are inside *'out_dir/posed_images/images'*. * Distortion-free images are inside *'out_dir/posed_images/images'*.
* Raw COLMAP intrinsics and poses are stored as a json file *'out_dir/posed_images/kai_cameras.json'*. * Raw COLMAP intrinsics and poses are stored as a json file *'out_dir/posed_images/kai_cameras.json'*.
* Normalized camderas are stored in *'out_dir/posed_images/kai_cameras_normalized.json'*. See the *'Scene normalization method'* in the *'Data'* section. * Normalized cameras are stored in *'out_dir/posed_images/kai_cameras_normalized.json'*. See the *'Scene normalization method'* in the *'Data'* section.
* Split distortion-free images and their correspoinding normalized cameras according to your need. * Split distortion-free images and their correspoinding normalized cameras according to your need.