📝 updating the documentation

FORK.md

@@ -21,7 +21,7 @@ pip3 install -r requirements.txt
 You will also need [COLMAP](colmap.github.io/)
 
 ## How to run
-
+### Dataset
 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).
 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
 ```
 
+### Camera pose estimation
 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
@@ -46,8 +47,7 @@ python3 run_colmap.py
 ```
 
 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`.
 
@@ -55,6 +55,11 @@ You again need to change the `input_path` and `output_path`.
 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
 `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.

colmap_runner/format_dataset.py

@@ -0,0 +1,94 @@
+"""Given the output of the run_colmap.py script, create a usable dataset
+compatible with the NeRF++ format. Made for Unix-like (posix style path), has
+not been tested for Windows."""
+
+import os
+import json
+import numpy as np
+import shutil
+
+input_path = "./lupo_output_dir_4"
+output_path = "./lupo_output_data_npp_3"
+
+# Read the JSON file containing all the data
+cam_dict_norm_path = os.path.join(input_path, "posed_images/kai_cameras_normalized.json")
+with open(cam_dict_norm_path) as fd:
+    cam_dict_norm = json.load(fd)
+
+# Make the train directories
+train_path = os.path.join(output_path, "train")
+train_int_path = os.path.join(train_path, "intrinsics")
+train_pose_path = os.path.join(train_path, "pose")
+train_rgb_path = os.path.join(train_path, "rgb")
+
+os.makedirs(train_path, exist_ok=True)
+os.makedirs(train_int_path, exist_ok=True)
+os.makedirs(train_pose_path, exist_ok=True)
+os.makedirs(train_rgb_path, exist_ok=True)
+
+# Make the train directories
+test_path = os.path.join(output_path, "test")
+test_int_path = os.path.join(test_path, "intrinsics")
+test_pose_path = os.path.join(test_path, "pose")
+test_rgb_path = os.path.join(test_path, "rgb")
+
+os.makedirs(test_path, exist_ok=True)
+os.makedirs(test_int_path, exist_ok=True)
+os.makedirs(test_pose_path, exist_ok=True)
+os.makedirs(test_rgb_path, exist_ok=True)
+
+# Sample images for the test set
+N = 10
+image_list = sorted(cam_dict_norm.keys())
+sampled = np.random.choice(image_list, N, replace=False)
+
+# Write the files with the corresponding data
+for img_name in sorted(cam_dict_norm.keys()):
+    # Retrieve the data
+    K = np.array(cam_dict_norm[img_name]['K'])
+    W2C = np.array(cam_dict_norm[img_name]['W2C'])
+
+    img_name_path = os.path.splitext(img_name)[0] # properly espace the extension
+    
+    # training set
+    if img_name not in sampled:
+        # Create the paths
+        train_int_img_path = os.path.join(train_int_path, img_name_path + ".txt") 
+        train_pose_img_path = os.path.join(train_pose_path, img_name_path + ".txt") 
+        train_rgb_img_path = os.path.join(train_rgb_path, img_name)
+
+        # Write intrinsics
+        with open(train_int_img_path, "w") as fd:
+            fd.write(" ".join(map(str, K)))
+
+        # Write poses
+        with open(train_pose_img_path, "w") as fd:
+            fd.write(" ".join(map(str, W2C)))
+
+        # Copy image
+        source_image_path = os.path.join(input_path, "posed_images/images", img_name)
+        shutil.copy(source_image_path, train_rgb_img_path)
+
+    # testing set
+    else:
+        # Create the paths
+        test_int_img_path = os.path.join(test_int_path, img_name_path + ".txt") 
+        test_pose_img_path = os.path.join(test_pose_path, img_name_path + ".txt") 
+        test_rgb_img_path = os.path.join(test_rgb_path, img_name)
+
+        # Write intrinsics
+        with open(test_int_img_path, "w") as fd:
+            fd.write(" ".join(map(str, K)))
+
+        # Write poses
+        with open(test_pose_img_path, "w") as fd:
+            fd.write(" ".join(map(str, W2C)))
+
+        # Copy image
+        source_image_path = os.path.join(input_path, "posed_images/images", img_name)
+        shutil.copy(source_image_path, test_rgb_img_path)
+
+
+# Create the validation dataset
+validation_path = os.path.join(output_path, "validation")
+os.symlink("./test", validation_path)