clustering_eps=80

handcrafted_solution.py

@@ -430,7 +430,7 @@ def prune_not_connected(all_3d_vertices, connections_3d):
     return np.array(new_verts), connected_out
 
 
-def predict(entry, visualize=False, scale_estimation_coefficient=2.5, clustering_eps = 100, **kwargs) -> Tuple[np.ndarray, List[int]]:
+def predict(entry, visualize=False, scale_estimation_coefficient=2.5, clustering_eps=100, **kwargs) -> Tuple[np.ndarray, List[int]]:
     if 'gestalt' not in entry or 'depthcm' not in entry or 'K' not in entry or 'R' not in entry or 't' not in entry:
         print('Missing required fields in the entry')
         return (entry['__key__'], *empty_solution())
@@ -441,31 +441,29 @@ def predict(entry, visualize=False, scale_estimation_coefficient=2.5, clustering
     for k, v in entry["images"].items():
         image_dict[v.name] = v
     points = [v.xyz for k, v in entry["points3d"].items()]
-    too_big = False
 
-    if not too_big:
-        points = np.array(points)
-        point_keys = [k for k, v in entry["points3d"].items()]
-        point_keys = np.array(point_keys)
+    points = np.array(points)
+    point_keys = [k for k, v in entry["points3d"].items()]
+    point_keys = np.array(point_keys)
 
-        # print(len(points))
+    # print(len(points))
 
-        clustered = DBSCAN(eps=clustering_eps, min_samples=10).fit(points).labels_
-        clustered_indices = np.argsort(clustered)
+    clustered = DBSCAN(eps=clustering_eps, min_samples=10).fit(points).labels_
+    clustered_indices = np.argsort(clustered)
 
-        points = points[clustered_indices]
-        point_keys = point_keys[clustered_indices]
-        clustered = clustered[clustered_indices]
+    points = points[clustered_indices]
+    point_keys = point_keys[clustered_indices]
+    clustered = clustered[clustered_indices]
 
-        _, cluster_indices = np.unique(clustered, return_index=True)
+    _, cluster_indices = np.unique(clustered, return_index=True)
 
-        clustered_points = np.split(points, cluster_indices[1:])
-        clustered_keys = np.split(point_keys, cluster_indices[1:])
+    clustered_points = np.split(points, cluster_indices[1:])
+    clustered_keys = np.split(point_keys, cluster_indices[1:])
 
-        biggest_cluster_index = np.argmax([len(i) for i in clustered_points])
-        # biggest_cluster = clustered_points[biggest_cluster_index]
-        biggest_cluster_keys = clustered_keys[biggest_cluster_index]
-        biggest_cluster_keys = set(biggest_cluster_keys)
+    biggest_cluster_index = np.argmax([len(i) for i in clustered_points])
+    # biggest_cluster = clustered_points[biggest_cluster_index]
+    biggest_cluster_keys = clustered_keys[biggest_cluster_index]
+    biggest_cluster_keys = set(biggest_cluster_keys)
 
     for i, (gest, depthcm, K, R, t, imagekey) in enumerate(zip(entry['gestalt'],
                                                                entry['depthcm'],
@@ -485,10 +483,7 @@ def predict(entry, visualize=False, scale_estimation_coefficient=2.5, clustering
                 continue
             belonging_points = []
             for i in image_dict[imagekey].point3D_ids[np.where(image_dict[imagekey].point3D_ids != -1)]:
-                if not too_big:
-                    if i in biggest_cluster_keys:
-                        belonging_points.append(entry["points3d"][i])
-                else:
+                if i in biggest_cluster_keys:
                     belonging_points.append(entry["points3d"][i])
 
             if len(belonging_points) < 1:

script.py

@@ -137,7 +137,7 @@ if __name__ == "__main__":
                                        merge_th=100.0,
                                        min_missing_distance=30000000.0,
                                        scale_estimation_coefficient=2.54,
-                                       clustering_eps=150,
+                                       clustering_eps=80,
                                        ))
         
         for i, result in enumerate(tqdm(results)):