3D boxes of instances in LIDAR coordinates. Coordinates in LiDAR: .. code-block:: none up z x front (yaw=-0.

3D boxes of instances in Depth coordinates. Coordinates in Depth: .. code-block:: none up z y front (yaw=-0.5*pi)

3D boxes of instances in CAM coordinates. Coordinates in camera: .. code-block:: none z front (yaw=-0.5*pi)

Points of instances in DEPTH coordinates. Args: tensor (torch.Tensor | np.ndarray | list): a N x points_dim matrix. points_dim (i

Points of instances in LIDAR coordinates. Args: tensor (torch.Tensor | np.ndarray | list): a N x points_dim matrix. points_dim (i

r"""ScanNet Dataset for Semantic Segmentation Task. This class serves as the API for experiments on the ScanNet Dataset. Please refer to the

Load Points From File. Load sunrgbd and scannet points from file. Args: coord_type (str): The type of coordinates of points cloud.

r"""S3DIS Dataset for Semantic Segmentation Task. This class serves as the API for experiments on the S3DIS Dataset. It wraps the provided da

r"""KITTI Dataset. This class serves as the API for experiments on the `KITTI Dataset <http://www.cvlibs.net/datasets/kitti/eval_object.php?o

r"""SUNRGBD Dataset. This class serves as the API for experiments on the SUNRGBD Dataset. See the `download page <http://rgbd.cs.princeton.e

Point set abstraction module with multi-scale grouping (MSG) used in PointNets. Args: num_point (int): Number of points. radi

Apply global rotation, scaling and translation to a 3D scene. Args: rot_range (list[float]): Range of rotation angle. Default

r"""Lyft Dataset. This class serves as the API for experiments on the Lyft Dataset. Please refer to `<https://www.kaggle.com/c/3d-object

r"""ScanNet Dataset for Detection Task. This class serves as the API for experiments on the ScanNet Dataset. Please refer to the `github rep

Base class for Points. Args: tensor (torch.Tensor | np.ndarray | list): a N x points_dim matrix. points_dim (int): Number of the

Points of instances in CAM coordinates. Args: tensor (torch.Tensor | np.ndarray | list): a N x points_dim matrix. points_dim (int

Map original semantic class to valid category ids. Map valid classes as 0~len(valid_cat_ids)-1 and others as len(valid_cat_ids). Args:

Load Annotations3D. Load instance mask and semantic mask of points and encapsulate the items into related fields. Args: with_bbo

Load points from multiple sweeps. This is usually used for nuScenes dataset to utilize previous sweeps. Args: sweeps_num (int): Numb

Non-CUDA version of PAConv. PAConv stores a trainable weight bank containing several kernel weights. Given input points and features, it comp

r"""Point set abstraction module with multi-scale grouping (MSG) used in PAConv networks. Replace the non CUDA version PAConv with CUDA imple

r"""Point set abstraction module with multi-scale grouping (MSG) used in PAConv networks. Replace the MLPs in `PointSAModuleMSG` with PAConv

PartA2 RoI head. Args: num_classes (int): The number of classes to prediction. seg_in_channels (int): Input channels of segmentat

Point sample. Sampling data to a certain number. Args: num_points (int): Number of points to be sampled. sample_range (float

r"""Randomly set the color of points to all zeros. Once this transform is executed, all the points' color will be dropped. Refer to `PAConv <

Randomly jitter point coordinates. Different from the global translation in ``GlobalRotScaleTrans``, here we \ apply different noises to

Vote module. Generate votes from seed point features. Args: in_channels (int): Number of channels of seed point features. vo

Voxel generator in numpy implementation. Args: voxel_size (list[float]): Size of a single voxel point_cloud_range (list[float]):

Waymo Dataset. This class serves as the API for experiments on the Waymo Dataset. Please refer to `<https://waymo.com/open/download/>`_for d

Filter background points near the bounding box. Args: bbox_enlarge_range (tuple[float], float): Bbox enlarge range.

r"""More general bbox head, with shared conv layers and two optional separated branches. .. code-block:: none /-> cls c

Base class for 3D Boxes. Note: The box is bottom centered, i.e. the relative position of origin in the box is (0.5, 0.5, 0).

Calculate Chamfer Distance of two sets. Args: mode (str): Criterion mode to calculate distance. The valid modes are smooth_l1

r"""Indoor point sample within a patch. Modified from `PointNet++ <https:// github.com/charlesq34/pointnet2/blob/master/scannet/scannet_dataset.py

Monocular 3D detection on KITTI Dataset. Args: data_root (str): Path of dataset root. info_file (str): Path of info file.

Dummy class for backward-compatibility. Same as DetectionEval.

r"""Monocular 3D detection on NuScenes Dataset. This class serves as the API for experiments on the NuScenes Dataset. Please refer to `NuSce

CUDA version of PAConv that implements a cuda op to efficiently perform kernel assembling. Different from vanilla PAConv, the input features

Point feature propagation module used in PointNets. Propagate the features from one set to another. Args: mlp_channels (list[int]):

3d residual block for ImVoxelNeck. Args: n_channels (int): Input channels of a feature map.

ScanNet data. Generate scannet infos for scannet_converter. Args: root_path (str): Root path of the raw data. split (str): S

ScanNet data. Generate scannet infos for scannet_converter. Args: root_path (str): Root path of the raw data. split (str): S

Sparse basic block for PartA^2. Sparse basic block implemented with submanifold sparse convolution. Args: inplanes (int): inplanes o

A wrapper of class sampled dataset with ann_file path. Implementation of paper `Class-balanced Grouping and Sampling for Point Cloud 3D Object

IoU Piece-wise Sampling. Sampling negtive proposals according to a list of IoU thresholds. The negtive proposals are divided into several pie

KITTI predictions to Waymo converter. This class serves as the converter to change predictions from KITTI to Waymo format. Args:

r"""NuScenes Dataset. This class serves as the API for experiments on the NuScenes Dataset. Please refer to `NuScenes Dataset <https://www.n

Calculate correlation loss of kernel weights in PAConv's weight bank. This is used as a regularization term in PAConv model training. Args:

Points sampling. Args: num_point (list[int]): Number of sample points. fps_mod_list (list[str]: Type of FPS method, valid mod

r"""S3DIS Dataset for Detection Task. This class is the inner dataset for S3DIS. Since S3DIS has 6 areas, we often train on 5 of them and tes

Squeeze-and-Excitation Module. Args: channels (int): The input (and output) channels of the SE layer. ratio (int): Squeeze ratio i

SUNRGBD data. Generate scannet infos for sunrgbd_converter. Args: root_path (str): Root path of the raw data. split (str): S

SUNRGBD data. Generate scannet infos for sunrgbd_converter. Args: root_path (str): Root path of the raw data. split (str): S

ScanNet dataset used to generate infos for semantic segmentation task. Args: data_root (str): Root path of the raw data. ann_file

ScanNet dataset used to generate infos for semantic segmentation task. Args: data_root (str): Root path of the raw data. ann_file

r"""Online visualizer implemented with Open3d. Args: points (numpy.array, shape=[N, 3+C]): Points to visualize. The Points cl

Axis-aligned 3D Overlaps (IoU) Calculator.

Class for sampling specific category of ground truths. Args: sample_list (list[dict]): List of samples. name (str | None): The ca

Default formatting bundle. It simplifies the pipeline of formatting common fields, including "img", "proposals", "gt_bboxes", "gt_labels", "g

Sampling Points. Sampling points with given index.

Apply global alignment to 3D scene points by rotation and translation. Args: rotation_axis (int): Rotation axis for points and bboxes rot

Group All. Group xyz with feature. Args: use_xyz (bool): Whether to use xyz.

Line instance in LIDAR coordinates

Line instance in LIDAR coordinates

Line instance in LIDAR coordinates

Line instance in LIDAR coordinates

Load an image from file in monocular 3D object detection. Compared to 2D detection, additional camera parameters need to be loaded. Args:

Load multi channel images from a list of separate channel files. Expects results['img_filename'] to be a list of filenames. Args: to

A simple MLP module. Pass features (B, C, N) through an MLP. Args: in_channels (int): Number of channels of input features.

Test-time augmentation with multiple scales and flipping. Args: transforms (list[dict]): Transforms to apply in each augmentation.

Normalize color of points. Args: color_mean (list[float]): Mean color of the point cloud.

Filter GT objects by their names. Args: classes (list[str]): List of class names to be kept for training.

Apply noise to each GT objects in the scene. Args: translation_std (list[float], optional): Standard deviation of the distrib

Filter objects by the range. Args: point_cloud_range (list[float]): Point cloud range.

Sample GT objects to the data. Args: db_sampler (dict): Config dict of the database sampler. sample_2d (bool): Whether to also pa

Pillar Feature Net Layer. The Pillar Feature Net is composed of a series of these layers, but the PointPillars paper results only used a sing

Image to Patch Embedding V2. We use a conv layer to implement PatchEmbed. Args: in_channels (int): The num of input channels. Default

Merge patch feature map. This layer use nn.Unfold to group feature map by kernel_size, and use norm and linear layer to embed grouped feature

Fuse image features from multi-scale features. Args: img_channels (list[int] | int): Channels of image features. It could be

Shuffle input points.

object candidate point prediction from seed point features. Args: in_channel (int): number of channels of seed point features. nu