Load camera parameters from calibration xml

data/create_syn_data.py

@@ -11,6 +11,8 @@ import os
 import collections
 import sys
 
+import xmltodict as xmltodict
+
 sys.path.append('../')
 import renderer
 import co
@@ -201,6 +203,16 @@ def create_data(out_root, idx, n_samples, imsize, patterns, K, baseline, blend_i
     print(f'create sample {idx + 1}/{n_samples} took {time.time() - tic}[s]')
 
 
+def load_camera_parameters():
+    with open('calibration_result.xml') as f:
+        cam_mat = xmltodict.parse(f.read())
+    # weird casting cause the values are str(float) (eg. '123.'), but we want int
+    imsize = [int(float(x)) for x in cam_mat['opencv_storage']['img_shape']['data'].split()]
+    K_shape = int(cam_mat['opencv_storage']['cam_int']['rows']), int(cam_mat['opencv_storage']['cam_int']['cols'])
+    K = np.array(cam_mat['opencv_storage']['cam_int']['data'].split(), dtype=float).reshape(K_shape).T
+    return imsize, K
+
+
 if __name__ == '__main__':
 
     np.random.seed(42)
@@ -230,11 +242,9 @@ if __name__ == '__main__':
     objs = get_objs(shapenet_root, obj_classes)
 
     # camera parameters
-    imsize = (488, 648)
+    imsize, K = load_camera_parameters()
     imsizes = [(imsize[0] // (2 ** s), imsize[1] // (2 ** s)) for s in range(4)]
-    # K = np.array([[567.6, 0, 324.7], [0, 570.2, 250.1], [0 ,0, 1]], dtype=np.float32)
+
-    K = np.array([[1929.5936336276382, 0, 113.66561071478046], [0, 1911.2517985448746, 473.70108079885887], [0, 0, 1]],
-                 dtype=np.float32)
     focal_lengths = [K[0, 0] / (2 ** s) for s in range(4)]
     baseline = 0.075
     blend_im = 0.6