hofee/nbv_reconstruction
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

ablation study

Browse Source
This commit is contained in:
hofee
2025-04-28 06:16:03 +00:00
parent ad7a1c9cdf
commit 81bf2678ac
7 changed files with 232 additions and 50 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
core/nbv_dataset.py
View File

@@ -135,7 +135,7 @@ class NBVReconstructionDataset(BaseDataset):
scanned_coverages_rate,
scanned_n_to_world_pose,
) = ([], [], [])
start_time = time.time()
#start_time = time.time()
start_indices = [0]
total_points = 0
for view in scanned_views:
@@ -163,7 +163,7 @@ class NBVReconstructionDataset(BaseDataset):
start_indices.append(total_points)
end_time = time.time()
#end_time = time.time()
#Log.info(f"load data time: {end_time - start_time}")
nbv_idx, nbv_coverage_rate = nbv[0], nbv[1]
nbv_path = DataLoadUtil.get_path(self.root_dir, scene_name, nbv_idx)
@@ -182,22 +182,22 @@ class NBVReconstructionDataset(BaseDataset):
voxel_downsampled_combined_scanned_pts_np, inverse = self.voxel_downsample_with_mapping(combined_scanned_views_pts, 0.003)
random_downsampled_combined_scanned_pts_np, random_downsample_idx = PtsUtil.random_downsample_point_cloud(voxel_downsampled_combined_scanned_pts_np, self.pts_num, require_idx=True)
all_idx_unique = np.arange(len(voxel_downsampled_combined_scanned_pts_np))
all_random_downsample_idx = all_idx_unique[random_downsample_idx]
scanned_pts_mask = []
for idx, start_idx in enumerate(start_indices):
if idx == len(start_indices) - 1:
break
end_idx = start_indices[idx+1]
view_inverse = inverse[start_idx:end_idx]
view_unique_downsampled_idx = np.unique(view_inverse)
view_unique_downsampled_idx_set = set(view_unique_downsampled_idx)
mask = np.array([idx in view_unique_downsampled_idx_set for idx in all_random_downsample_idx])
scanned_pts_mask.append(mask)
# all_idx_unique = np.arange(len(voxel_downsampled_combined_scanned_pts_np))
# all_random_downsample_idx = all_idx_unique[random_downsample_idx]
# scanned_pts_mask = []
# for idx, start_idx in enumerate(start_indices):
# if idx == len(start_indices) - 1:
# break
# end_idx = start_indices[idx+1]
# view_inverse = inverse[start_idx:end_idx]
# view_unique_downsampled_idx = np.unique(view_inverse)
# view_unique_downsampled_idx_set = set(view_unique_downsampled_idx)
# mask = np.array([idx in view_unique_downsampled_idx_set for idx in all_random_downsample_idx])
# #scanned_pts_mask.append(mask)
data_item = {
"scanned_pts": np.asarray(scanned_views_pts, dtype=np.float32), # Ndarray(S x Nv x 3)
"combined_scanned_pts": np.asarray(random_downsampled_combined_scanned_pts_np, dtype=np.float32), # Ndarray(N x 3)
"scanned_pts_mask": np.asarray(scanned_pts_mask, dtype=np.bool), # Ndarray(N)
#"scanned_pts_mask": np.asarray(scanned_pts_mask, dtype=np.bool), # Ndarray(N)
"scanned_coverage_rate": scanned_coverages_rate, # List(S): Float, range(0, 1)
"scanned_n_to_world_pose_9d": np.asarray(scanned_n_to_world_pose, dtype=np.float32), # Ndarray(S x 9)
"best_coverage_rate": nbv_coverage_rate, # Float, range(0, 1)
@@ -223,9 +223,9 @@ class NBVReconstructionDataset(BaseDataset):
collate_data["scanned_n_to_world_pose_9d"] = [
torch.tensor(item["scanned_n_to_world_pose_9d"]) for item in batch
]
collate_data["scanned_pts_mask"] = [
torch.tensor(item["scanned_pts_mask"]) for item in batch
]
# collate_data["scanned_pts_mask"] = [
# torch.tensor(item["scanned_pts_mask"]) for item in batch
# ]
''' ------ Fixed Length ------ '''
collate_data["best_to_world_pose_9d"] = torch.stack(