best mean=1.7695378948997886

point_radius=45,
max_angle=15,
extend=25,
merge_th=80.0,
min_missing_distance=1000.0,
scale_estimation_coefficient=2.54,
clustering_eps=150,
interpolation_radius=10000,
point_radius_scale=0.5,
# dist_coeff=0,
pointcloud_depth_coeff=1.005,

removed blur
decreased number of dilations to 2
decreased kernel size to 11
decreased color range to 3.5
moved vertice stop condition after inferring the missing vertices
added mean interpolation k = 5

handcrafted_solution.py

@@ -42,10 +42,32 @@ class NearestNDInterpolatorWithThreshold(si.NearestNDInterpolator):
     def __call__(self, *args):
         # Convert the input to a 2D array of query points
         query_points = np.array(args).T
-        distances, indices = self.tree.query(query_points)
-        values = np.full(query_points.shape[:-1], np.nan)
-        valid_mask = distances <= self.max_distance
-        values[valid_mask] = self.values[indices[valid_mask]]
+        distances, indices = self.tree.query(query_points, k=5, distance_upper_bound=self.max_distance)
+        # valid_mask = distances <= self.max_distance
+        # print(indices)
+        # print(distances)
+        # distances = np.mean(distances, axis=1)
+        # print(indices)
+        # print(self.values)# print(distances)
+
+        found_mask = indices != len(self.values)
+        temp_values = np.concatenate([self.values, [0]])
+        values = temp_values[indices]
+        # values[~found_mask] = 0
+
+        values = np.sum(values, axis=1)
+        found_mask_sum = np.sum(found_mask, axis=1)
+        found_mask = found_mask_sum != 0
+        values[found_mask] /= found_mask_sum[found_mask]
+
+        values[~found_mask] = np.nan
+
+        # print(values)
+        # np.ma.masked_where(indices, found_mask)
+
+        # print(self.values[indices[found_mask]])
+        # values[found_mask] =
+        # print(values)
         return values.T
 def empty_solution():
     '''Return a minimal valid solution, i.e. 2 vertices and 1 edge.'''

script.py

@@ -145,7 +145,7 @@ if __name__ == "__main__":
                                            point_radius=45,
                                            max_angle=15,
                                            extend=25,
-                                           merge_th=100.0,
+                                           merge_th=80.0,
                                            min_missing_distance=1000.0,
                                            scale_estimation_coefficient=2.54,
                                            clustering_eps=150,