src/StructDiffusion/utils/pointnet.py

import torch
import torch.nn as nn
import torch.nn.functional as F
from time import time
import numpy as np


# reference https://github.com/yanx27/Pointnet_Pointnet2_pytorch, modified by Yang You


def timeit(tag, t):
    print("{}: {}s".format(tag, time() - t))
    return time()

def pc_normalize(pc):
    if type(pc).__module__ == np.__name__:
        centroid = np.mean(pc, axis=0)
        pc = pc - centroid
        m = np.max(np.sqrt(np.sum(pc**2, axis=1)))
        pc = pc / m
    else:
        centroid = torch.mean(pc, dim=0)
        pc = pc - centroid
        m = torch.max(torch.sqrt(torch.sum(pc ** 2, dim=1)))
        pc = pc / m
    return pc

def square_distance(src, dst):
    """
    Calculate Euclid distance between each two points.
    src^T * dst = xn * xm + yn * ym + zn * zm；
    sum(src^2, dim=-1) = xn*xn + yn*yn + zn*zn;
    sum(dst^2, dim=-1) = xm*xm + ym*ym + zm*zm;
    dist = (xn - xm)^2 + (yn - ym)^2 + (zn - zm)^2
         = sum(src**2,dim=-1)+sum(dst**2,dim=-1)-2*src^T*dst
    Input:
        src: source points, [B, N, C]
        dst: target points, [B, M, C]
    Output:
        dist: per-point square distance, [B, N, M]
    """
    return torch.sum((src[:, :, None] - dst[:, None]) ** 2, dim=-1)


def index_points(points, idx):
    """
    Input:
        points: input points data, [B, N, C]
        idx: sample index data, [B, S, [K]]
    Return:
        new_points:, indexed points data, [B, S, [K], C]
    """
    raw_size = idx.size()
    idx = idx.reshape(raw_size[0], -1)
    res = torch.gather(points, 1, idx[..., None].expand(-1, -1, points.size(-1)))
    return res.reshape(*raw_size, -1)


def farthest_point_sample(xyz, npoint):
    """
    Input:
        xyz: pointcloud data, [B, N, 3]
        npoint: number of samples
    Return:
        centroids: sampled pointcloud index, [B, npoint]
    """
    device = xyz.device
    B, N, C = xyz.shape
    centroids = torch.zeros(B, npoint, dtype=torch.long).to(device)
    distance = torch.ones(B, N).to(device) * 1e10
    farthest = torch.randint(0, N, (B,), dtype=torch.long).to(device)
    batch_indices = torch.arange(B, dtype=torch.long).to(device)
    for i in range(npoint):
        centroids[:, i] = farthest
        centroid = xyz[batch_indices, farthest, :].view(B, 1, 3)
        dist = torch.sum((xyz - centroid) ** 2, -1)
        distance = torch.min(distance, dist)
        farthest = torch.max(distance, -1)[1]
    return centroids


def random_point_sample(xyz, npoint):
    """
    Input:
        xyz: pointcloud data, [B, N, 3]
        npoint: number of samples
    Return:
        idxs: sampled pointcloud index, [B, npoint]
    """
    device = xyz.device
    B, N, C = xyz.shape
    idxs = torch.randint(0, N, (B, npoint), dtype=torch.long).to(device)
    return idxs


def query_ball_point(radius, nsample, xyz, new_xyz):
    """
    Input:
        radius: local region radius
        nsample: max sample number in local region
        xyz: all points, [B, N, 3]
        new_xyz: query points, [B, S, 3]
    Return:
        group_idx: grouped points index, [B, S, nsample]
    """
    device = xyz.device
    B, N, C = xyz.shape
    _, S, _ = new_xyz.shape
    group_idx = torch.arange(N, dtype=torch.long).to(device).view(1, 1, N).repeat([B, S, 1])
    sqrdists = square_distance(new_xyz, xyz)
    group_idx[sqrdists > radius ** 2] = N
    group_idx = group_idx.sort(dim=-1)[0][:, :, :nsample]
    group_first = group_idx[:, :, 0].view(B, S, 1).repeat([1, 1, nsample])
    mask = group_idx == N
    group_idx[mask] = group_first[mask]
    return group_idx


def sample_and_group(npoint, radius, nsample, xyz, points, returnfps=False, knn=False):
    """
    Input:
        npoint:
        radius:
        nsample:
        xyz: input points position data, [B, N, 3]
        points: input points data, [B, N, D]
    Return:
        new_xyz: sampled points position data, [B, npoint, nsample, 3]
        new_points: sampled points data, [B, npoint, nsample, 3+D]
    """
    B, N, C = xyz.shape
    S = npoint
    fps_idx = farthest_point_sample(xyz, npoint) # [B, npoint]
    torch.cuda.empty_cache()
    new_xyz = index_points(xyz, fps_idx)
    torch.cuda.empty_cache()
    if knn:
        dists = square_distance(new_xyz, xyz)  # B x npoint x N
        idx = dists.argsort()[:, :, :nsample]  # B x npoint x K
    else:
        idx = query_ball_point(radius, nsample, xyz, new_xyz)
    torch.cuda.empty_cache()
    grouped_xyz = index_points(xyz, idx) # [B, npoint, nsample, C]
    torch.cuda.empty_cache()
    grouped_xyz_norm = grouped_xyz - new_xyz.view(B, S, 1, C)
    torch.cuda.empty_cache()

    if points is not None:
        grouped_points = index_points(points, idx)
        new_points = torch.cat([grouped_xyz_norm, grouped_points], dim=-1) # [B, npoint, nsample, C+D]
    else:
        new_points = grouped_xyz_norm
    if returnfps:
        return new_xyz, new_points, grouped_xyz, fps_idx
    else:
        return new_xyz, new_points


def sample_and_group_all(xyz, points):
    """
    Input:
        xyz: input points position data, [B, N, 3]
        points: input points data, [B, N, D]
    Return:
        new_xyz: sampled points position data, [B, 1, 3]
        new_points: sampled points data, [B, 1, N, 3+D]
    """
    device = xyz.device
    B, N, C = xyz.shape
    new_xyz = torch.zeros(B, 1, C).to(device)
    grouped_xyz = xyz.view(B, 1, N, C)
    if points is not None:
        new_points = torch.cat([grouped_xyz, points.view(B, 1, N, -1)], dim=-1)
    else:
        new_points = grouped_xyz
    return new_xyz, new_points


class PointNetSetAbstraction(nn.Module):
    def __init__(self, npoint, radius, nsample, in_channel, mlp, group_all, knn=False):
        super(PointNetSetAbstraction, self).__init__()
        self.npoint = npoint
        self.radius = radius
        self.nsample = nsample
        self.knn = knn
        self.mlp_convs = nn.ModuleList()
        self.mlp_bns = nn.ModuleList()
        last_channel = in_channel
        for out_channel in mlp:
            self.mlp_convs.append(nn.Conv2d(last_channel, out_channel, 1))
            self.mlp_bns.append(nn.BatchNorm2d(out_channel))
            last_channel = out_channel
        self.group_all = group_all

    def forward(self, xyz, points):
        """
        Input:
            xyz: input points position data, [B, N, C]
            points: input points data, [B, N, C]
        Return:
            new_xyz: sampled points position data, [B, S, C]
            new_points_concat: sample points feature data, [B, S, D']
        """
        if self.group_all:
            new_xyz, new_points = sample_and_group_all(xyz, points)
        else:
            new_xyz, new_points = sample_and_group(self.npoint, self.radius, self.nsample, xyz, points, knn=self.knn)
        # new_xyz: sampled points position data, [B, npoint, C]
        # new_points: sampled points data, [B, npoint, nsample, C+D]
        new_points = new_points.permute(0, 3, 2, 1) # [B, C+D, nsample,npoint]
        for i, conv in enumerate(self.mlp_convs):
            bn = self.mlp_bns[i]
            new_points =  F.relu(bn(conv(new_points)))

        new_points = torch.max(new_points, 2)[0].transpose(1, 2)
        return new_xyz, new_points


class PointNetSetAbstractionMsg(nn.Module):
    def __init__(self, npoint, radius_list, nsample_list, in_channel, mlp_list, knn=False):
        super(PointNetSetAbstractionMsg, self).__init__()
        self.npoint = npoint
        self.radius_list = radius_list
        self.nsample_list = nsample_list
        self.knn = knn
        self.conv_blocks = nn.ModuleList()
        self.bn_blocks = nn.ModuleList()
        for i in range(len(mlp_list)):
            convs = nn.ModuleList()
            bns = nn.ModuleList()
            last_channel = in_channel + 3
            for out_channel in mlp_list[i]:
                convs.append(nn.Conv2d(last_channel, out_channel, 1))
                bns.append(nn.BatchNorm2d(out_channel))
                last_channel = out_channel
            self.conv_blocks.append(convs)
            self.bn_blocks.append(bns)

    def forward(self, xyz, points, seed_idx=None):
        """
        Input:
            xyz: input points position data, [B, C, N]
            points: input points data, [B, D, N]
        Return:
            new_xyz: sampled points position data, [B, C, S]
            new_points_concat: sample points feature data, [B, D', S]
        """

        B, N, C = xyz.shape
        S = self.npoint
        new_xyz = index_points(xyz, farthest_point_sample(xyz, S) if seed_idx is None else seed_idx)
        new_points_list = []
        for i, radius in enumerate(self.radius_list):
            K = self.nsample_list[i]
            if self.knn:
                dists = square_distance(new_xyz, xyz)  # B x npoint x N
                group_idx = dists.argsort()[:, :, :K]  # B x npoint x K
            else:
                group_idx = query_ball_point(radius, K, xyz, new_xyz)
            grouped_xyz = index_points(xyz, group_idx)
            grouped_xyz -= new_xyz.view(B, S, 1, C)
            if points is not None:
                grouped_points = index_points(points, group_idx)
                grouped_points = torch.cat([grouped_points, grouped_xyz], dim=-1)
            else:
                grouped_points = grouped_xyz

            grouped_points = grouped_points.permute(0, 3, 2, 1)  # [B, D, K, S]
            for j in range(len(self.conv_blocks[i])):
                conv = self.conv_blocks[i][j]
                bn = self.bn_blocks[i][j]
                grouped_points =  F.relu(bn(conv(grouped_points)))
            new_points = torch.max(grouped_points, 2)[0]  # [B, D', S]
            new_points_list.append(new_points)

        new_points_concat = torch.cat(new_points_list, dim=1).transpose(1, 2)
        return new_xyz, new_points_concat


# NoteL this function swaps N and C
class PointNetFeaturePropagation(nn.Module):
    def __init__(self, in_channel, mlp):
        super(PointNetFeaturePropagation, self).__init__()
        self.mlp_convs = nn.ModuleList()
        self.mlp_bns = nn.ModuleList()
        last_channel = in_channel
        for out_channel in mlp:
            self.mlp_convs.append(nn.Conv1d(last_channel, out_channel, 1))
            self.mlp_bns.append(nn.BatchNorm1d(out_channel))
            last_channel = out_channel

    def forward(self, xyz1, xyz2, points1, points2):
        """
        Input:
            xyz1: input points position data, [B, C, N]
            xyz2: sampled input points position data, [B, C, S]
            points1: input points data, [B, D, N]
            points2: input points data, [B, D, S]
        Return:
            new_points: upsampled points data, [B, D', N]
        """
        xyz1 = xyz1.permute(0, 2, 1)
        xyz2 = xyz2.permute(0, 2, 1)

        points2 = points2.permute(0, 2, 1)
        B, N, C = xyz1.shape
        _, S, _ = xyz2.shape

        if S == 1:
            interpolated_points = points2.repeat(1, N, 1)
        else:
            dists = square_distance(xyz1, xyz2)
            dists, idx = dists.sort(dim=-1)
            dists, idx = dists[:, :, :3], idx[:, :, :3]  # [B, N, 3]

            dist_recip = 1.0 / (dists + 1e-8)
            norm = torch.sum(dist_recip, dim=2, keepdim=True)
            weight = dist_recip / norm
            interpolated_points = torch.sum(index_points(points2, idx) * weight.view(B, N, 3, 1), dim=2)

        if points1 is not None:
            points1 = points1.permute(0, 2, 1)
            new_points = torch.cat([points1, interpolated_points], dim=-1)
        else:
            new_points = interpolated_points

        new_points = new_points.permute(0, 2, 1)
        for i, conv in enumerate(self.mlp_convs):
            bn = self.mlp_bns[i]
            new_points = F.relu(bn(conv(new_points)))
        return new_points


# reference https://github.com/qq456cvb/Point-Transformers

def normalize_data(batch_data):
    """ Normalize the batch data, use coordinates of the block centered at origin,
        Input:
            BxNxC array
        Output:
            BxNxC array
    """
    B, N, C = batch_data.shape
    normal_data = np.zeros((B, N, C))
    for b in range(B):
        pc = batch_data[b]
        centroid = np.mean(pc, axis=0)
        pc = pc - centroid
        m = np.max(np.sqrt(np.sum(pc ** 2, axis=1)))
        pc = pc / m
        normal_data[b] = pc
    return normal_data


def shuffle_data(data, labels):
    """ Shuffle data and labels.
        Input:
          data: B,N,... numpy array
          label: B,... numpy array
        Return:
          shuffled data, label and shuffle indices
    """
    idx = np.arange(len(labels))
    np.random.shuffle(idx)
    return data[idx, ...], labels[idx], idx

def shuffle_points(batch_data):
    """ Shuffle orders of points in each point cloud -- changes FPS behavior.
        Use the same shuffling idx for the entire batch.
        Input:
            BxNxC array
        Output:
            BxNxC array
    """
    idx = np.arange(batch_data.shape[1])
    np.random.shuffle(idx)
    return batch_data[:,idx,:]

def rotate_point_cloud(batch_data):
    """ Randomly rotate the point clouds to augument the dataset
        rotation is per shape based along up direction
        Input:
          BxNx3 array, original batch of point clouds
        Return:
          BxNx3 array, rotated batch of point clouds
    """
    rotated_data = np.zeros(batch_data.shape, dtype=np.float32)
    for k in range(batch_data.shape[0]):
        rotation_angle = np.random.uniform() * 2 * np.pi
        cosval = np.cos(rotation_angle)
        sinval = np.sin(rotation_angle)
        rotation_matrix = np.array([[cosval, 0, sinval],
                                    [0, 1, 0],
                                    [-sinval, 0, cosval]])
        shape_pc = batch_data[k, ...]
        rotated_data[k, ...] = np.dot(shape_pc.reshape((-1, 3)), rotation_matrix)
    return rotated_data

def rotate_point_cloud_z(batch_data):
    """ Randomly rotate the point clouds to augument the dataset
        rotation is per shape based along up direction
        Input:
          BxNx3 array, original batch of point clouds
        Return:
          BxNx3 array, rotated batch of point clouds
    """
    rotated_data = np.zeros(batch_data.shape, dtype=np.float32)
    for k in range(batch_data.shape[0]):
        rotation_angle = np.random.uniform() * 2 * np.pi
        cosval = np.cos(rotation_angle)
        sinval = np.sin(rotation_angle)
        rotation_matrix = np.array([[cosval, sinval, 0],
                                    [-sinval, cosval, 0],
                                    [0, 0, 1]])
        shape_pc = batch_data[k, ...]
        rotated_data[k, ...] = np.dot(shape_pc.reshape((-1, 3)), rotation_matrix)
    return rotated_data

def rotate_point_cloud_with_normal(batch_xyz_normal):
    ''' Randomly rotate XYZ, normal point cloud.
        Input:
            batch_xyz_normal: B,N,6, first three channels are XYZ, last 3 all normal
        Output:
            B,N,6, rotated XYZ, normal point cloud
    '''
    for k in range(batch_xyz_normal.shape[0]):
        rotation_angle = np.random.uniform() * 2 * np.pi
        cosval = np.cos(rotation_angle)
        sinval = np.sin(rotation_angle)
        rotation_matrix = np.array([[cosval, 0, sinval],
                                    [0, 1, 0],
                                    [-sinval, 0, cosval]])
        shape_pc = batch_xyz_normal[k,:,0:3]
        shape_normal = batch_xyz_normal[k,:,3:6]
        batch_xyz_normal[k,:,0:3] = np.dot(shape_pc.reshape((-1, 3)), rotation_matrix)
        batch_xyz_normal[k,:,3:6] = np.dot(shape_normal.reshape((-1, 3)), rotation_matrix)
    return batch_xyz_normal

def rotate_perturbation_point_cloud_with_normal(batch_data, angle_sigma=0.06, angle_clip=0.18):
    """ Randomly perturb the point clouds by small rotations
        Input:
          BxNx6 array, original batch of point clouds and point normals
        Return:
          BxNx3 array, rotated batch of point clouds
    """
    rotated_data = np.zeros(batch_data.shape, dtype=np.float32)
    for k in range(batch_data.shape[0]):
        angles = np.clip(angle_sigma*np.random.randn(3), -angle_clip, angle_clip)
        Rx = np.array([[1,0,0],
                       [0,np.cos(angles[0]),-np.sin(angles[0])],
                       [0,np.sin(angles[0]),np.cos(angles[0])]])
        Ry = np.array([[np.cos(angles[1]),0,np.sin(angles[1])],
                       [0,1,0],
                       [-np.sin(angles[1]),0,np.cos(angles[1])]])
        Rz = np.array([[np.cos(angles[2]),-np.sin(angles[2]),0],
                       [np.sin(angles[2]),np.cos(angles[2]),0],
                       [0,0,1]])
        R = np.dot(Rz, np.dot(Ry,Rx))
        shape_pc = batch_data[k,:,0:3]
        shape_normal = batch_data[k,:,3:6]
        rotated_data[k,:,0:3] = np.dot(shape_pc.reshape((-1, 3)), R)
        rotated_data[k,:,3:6] = np.dot(shape_normal.reshape((-1, 3)), R)
    return rotated_data


def rotate_point_cloud_by_angle(batch_data, rotation_angle):
    """ Rotate the point cloud along up direction with certain angle.
        Input:
          BxNx3 array, original batch of point clouds
        Return:
          BxNx3 array, rotated batch of point clouds
    """
    rotated_data = np.zeros(batch_data.shape, dtype=np.float32)
    for k in range(batch_data.shape[0]):
        #rotation_angle = np.random.uniform() * 2 * np.pi
        cosval = np.cos(rotation_angle)
        sinval = np.sin(rotation_angle)
        rotation_matrix = np.array([[cosval, 0, sinval],
                                    [0, 1, 0],
                                    [-sinval, 0, cosval]])
        shape_pc = batch_data[k,:,0:3]
        rotated_data[k,:,0:3] = np.dot(shape_pc.reshape((-1, 3)), rotation_matrix)
    return rotated_data

def rotate_point_cloud_by_angle_with_normal(batch_data, rotation_angle):
    """ Rotate the point cloud along up direction with certain angle.
        Input:
          BxNx6 array, original batch of point clouds with normal
          scalar, angle of rotation
        Return:
          BxNx6 array, rotated batch of point clouds iwth normal
    """
    rotated_data = np.zeros(batch_data.shape, dtype=np.float32)
    for k in range(batch_data.shape[0]):
        #rotation_angle = np.random.uniform() * 2 * np.pi
        cosval = np.cos(rotation_angle)
        sinval = np.sin(rotation_angle)
        rotation_matrix = np.array([[cosval, 0, sinval],
                                    [0, 1, 0],
                                    [-sinval, 0, cosval]])
        shape_pc = batch_data[k,:,0:3]
        shape_normal = batch_data[k,:,3:6]
        rotated_data[k,:,0:3] = np.dot(shape_pc.reshape((-1, 3)), rotation_matrix)
        rotated_data[k,:,3:6] = np.dot(shape_normal.reshape((-1,3)), rotation_matrix)
    return rotated_data



def rotate_perturbation_point_cloud(batch_data, angle_sigma=0.06, angle_clip=0.18):
    """ Randomly perturb the point clouds by small rotations
        Input:
          BxNx3 array, original batch of point clouds
        Return:
          BxNx3 array, rotated batch of point clouds
    """
    rotated_data = np.zeros(batch_data.shape, dtype=np.float32)
    for k in range(batch_data.shape[0]):
        angles = np.clip(angle_sigma*np.random.randn(3), -angle_clip, angle_clip)
        Rx = np.array([[1,0,0],
                       [0,np.cos(angles[0]),-np.sin(angles[0])],
                       [0,np.sin(angles[0]),np.cos(angles[0])]])
        Ry = np.array([[np.cos(angles[1]),0,np.sin(angles[1])],
                       [0,1,0],
                       [-np.sin(angles[1]),0,np.cos(angles[1])]])
        Rz = np.array([[np.cos(angles[2]),-np.sin(angles[2]),0],
                       [np.sin(angles[2]),np.cos(angles[2]),0],
                       [0,0,1]])
        R = np.dot(Rz, np.dot(Ry,Rx))
        shape_pc = batch_data[k, ...]
        rotated_data[k, ...] = np.dot(shape_pc.reshape((-1, 3)), R)
    return rotated_data


def jitter_point_cloud(batch_data, sigma=0.01, clip=0.05):
    """ Randomly jitter points. jittering is per point.
        Input:
          BxNx3 array, original batch of point clouds
        Return:
          BxNx3 array, jittered batch of point clouds
    """
    B, N, C = batch_data.shape
    assert(clip > 0)
    jittered_data = np.clip(sigma * np.random.randn(B, N, C), -1*clip, clip)
    jittered_data += batch_data
    return jittered_data

def shift_point_cloud(batch_data, shift_range=0.1):
    """ Randomly shift point cloud. Shift is per point cloud.
        Input:
          BxNx3 array, original batch of point clouds
        Return:
          BxNx3 array, shifted batch of point clouds
    """
    B, N, C = batch_data.shape
    shifts = np.random.uniform(-shift_range, shift_range, (B,3))
    for batch_index in range(B):
        batch_data[batch_index,:,:] += shifts[batch_index,:]
    return batch_data


def random_scale_point_cloud(batch_data, scale_low=0.8, scale_high=1.25):
    """ Randomly scale the point cloud. Scale is per point cloud.
        Input:
            BxNx3 array, original batch of point clouds
        Return:
            BxNx3 array, scaled batch of point clouds
    """
    B, N, C = batch_data.shape
    scales = np.random.uniform(scale_low, scale_high, B)
    for batch_index in range(B):
        batch_data[batch_index,:,:] *= scales[batch_index]
    return batch_data

def random_point_dropout(batch_pc, max_dropout_ratio=0.875):
    ''' batch_pc: BxNx3 '''
    for b in range(batch_pc.shape[0]):
        dropout_ratio =  np.random.random()*max_dropout_ratio # 0~0.875
        drop_idx = np.where(np.random.random((batch_pc.shape[1]))<=dropout_ratio)[0]
        if len(drop_idx)>0:
            batch_pc[b,drop_idx,:] = batch_pc[b,0,:] # set to the first point
    return batch_pc