Merge branch 'main' of https://github.com/philippwulff/D-NeRF into main

README.md

@@ -27,9 +27,13 @@ If you want to directly explore the models or use our training data, you can dow
 ```
 
 *Download Datasets*
+
 **DeepDeform**. This is a RGB-D dataset of dynamic scenes with fixed camera poses. You can request access on the project's [GitHub page](https://github.com/AljazBozic/DeepDeform).
+
 **Own Data**. Download from [here](https://drive.google.com/drive/folders/1hUv1UZfxtmqVtushTH2_obexMv7mVu8L?usp=sharing).
 
+**Generate Own scenes** Own scenes can be easily generated and integrated. We used an iPAD with Lidar Sensor (App: Record3d --> export Videos as EXR + RGB). Extract dataset to correct format by running load_owndataset.py (Specifiy correct args in main and create a scene configuration entry).
+
 ## How to Use It
 
 If you have downloaded the pre-trained, you can test models without training them. Otherwise, download our or you own data to train a model.
@@ -41,7 +45,6 @@ You can use these jupyter notebooks to explore the model.
 | ----------- | ----------- |
 | Synthesize novel views at an arbitrary point in time. (Requires trained model) | render.ipynb|
 | Reconstruct the mesh at an arbitrary point in time. (Requires trained model) | reconstruct.ipynb|
-| Quantitatively evaluate trained models. | metrics.ipynb|
 | See the camera trajectory of the training frames or novel views. | eda_virtual_camera.ipynb|
 | Visualize the sampling along camera rays. (Requires training logs) | eda_ray_sampling.ipynb|
 
@@ -51,12 +54,12 @@ First download the dataset. Then,
 conda activate dnerf
 export PYTHONPATH='path/to/D-NeRF'
 export CUDA_VISIBLE_DEVICES=0
-python run_dnerf.py --config configs/mutant.txt
+python run_dnerf.py --config configs/johannes.txt
 ```
 
 ### Test
 First download pre-trained weights and dataset. Then, 
 ```
 python run_dnerf.py --config configs/johannes.txt --render_only --render_test
 ```
-This command will run the `johannes` experiment. When finished, results are saved to `./logs/johannes/renderonly_test_799999`. To quantitatively evaluate model run the `metrics.ipynb` notebook.
+This command will run the `johannes` experiment. When finished, results are saved to `./logs/johannes/renderonly_test_799999`. The quantitative results are stored inside the testrun folder under "metrics.txt".