|
|
@ -21,7 +21,7 @@ pip3 install -r requirements.txt
|
|
|
|
You will also need [COLMAP](colmap.github.io/)
|
|
|
|
You will also need [COLMAP](colmap.github.io/)
|
|
|
|
|
|
|
|
|
|
|
|
## How to run
|
|
|
|
## How to run
|
|
|
|
|
|
|
|
### Dataset
|
|
|
|
First you need to create or find a dataset. A large set of images (at least 30,
|
|
|
|
First you need to create or find a dataset. A large set of images (at least 30,
|
|
|
|
more if you want a 360 degree reconstruction).
|
|
|
|
more if you want a 360 degree reconstruction).
|
|
|
|
In order to maximise the quality of the reconstuction it is recommended to take
|
|
|
|
In order to maximise the quality of the reconstuction it is recommended to take
|
|
|
@ -34,6 +34,7 @@ with tools like ImageMagick (mogrify or convert)
|
|
|
|
mogrify -resize 800 *.jpg
|
|
|
|
mogrify -resize 800 *.jpg
|
|
|
|
```
|
|
|
|
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
### Camera pose estimation
|
|
|
|
Then use the wrapper colmap `colmap_runner/run_colmap.py`
|
|
|
|
Then use the wrapper colmap `colmap_runner/run_colmap.py`
|
|
|
|
|
|
|
|
|
|
|
|
First change the two lines corresponding to input and output at the end of the
|
|
|
|
First change the two lines corresponding to input and output at the end of the
|
|
|
@ -46,8 +47,7 @@ python3 run_colmap.py
|
|
|
|
```
|
|
|
|
```
|
|
|
|
|
|
|
|
|
|
|
|
Then you will need to use the `format_dataset.py` script to transform the
|
|
|
|
Then you will need to use the `format_dataset.py` script to transform the
|
|
|
|
wrapper COLMAP binary format data into the datastructure requirements by
|
|
|
|
wrapper COLMAP binary format data into the datastructure required by NeRF++.
|
|
|
|
NeRF++.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
You again need to change the `input_path` and `output_path`.
|
|
|
|
You again need to change the `input_path` and `output_path`.
|
|
|
|
|
|
|
|
|
|
|
@ -55,6 +55,11 @@ You again need to change the `input_path` and `output_path`.
|
|
|
|
python3 format_dataset.py
|
|
|
|
python3 format_dataset.py
|
|
|
|
```
|
|
|
|
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Before training you can visualise your camera poses using the
|
|
|
|
|
|
|
|
`camera_visualizer/visualize_cameras.py` script.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
### Training the model
|
|
|
|
|
|
|
|
|
|
|
|
You then need to create the configuration file, copying the example in
|
|
|
|
You then need to create the configuration file, copying the example in
|
|
|
|
`configs` and tweaking the values to your need is recommended. Refer to the
|
|
|
|
`configs` and tweaking the values to your need is recommended. Refer to the
|
|
|
|
help inside `ddp_train_nerf.py` if you need to understand a parameter.
|
|
|
|
help inside `ddp_train_nerf.py` if you need to understand a parameter.
|
|
|
|