文章目录

• 点云补全概念
• • 点云补全（PF-Net）
  • 点云补全网络模型
  • • 骨骼点逐级恢复点云
    • 最远点采样
    • 特征提取
    • 分层预测
    • Chamfer Distance
    • GAN
    • BCELoss损失模块
• 点云补全项目应用

点云补全概念

点云补全就是希望基于观察到的残缺不全的点云生成完整的 3D 点云。由于扫描或者距离的原因导致点云局部缺失，对其进行补全，传统算法可能会补不完整，也可能会补的过于完整。

点云补全（PF-Net）

今天这里要讲的是PF-Net: Point Fractal Network for 3D Point Cloud Completion，整体网络模型：

点云补全网络模型

骨骼点逐级恢复点云

最远点采样

• 利用骨骼点来逐级恢复点云
• 在构建标签时依旧选择最远点采样

特征提取

• 特征提取，融合多尺度特征，信息更丰富
  

PF-Net特征提取代码实现如下：

def forward(self,x):        print(x.shape)        x = torch.unsqueeze(x,1)        print(x.shape)        x = F.relu(self.bn1(self.conv1(x)))        print(x.shape)        x = F.relu(self.bn2(self.conv2(x)))        print(x.shape)        x_128 = F.relu(self.bn3(self.conv3(x)))        print(x_128.shape)        x_256 = F.relu(self.bn4(self.conv4(x_128)))        x_512 = F.relu(self.bn5(self.conv5(x_256)))        x_1024 = F.relu(self.bn6(self.conv6(x_512)))        print(x_1024.shape)        x_128 = torch.squeeze(self.maxpool(x_128),2)        print(x_128.shape)        x_256 = torch.squeeze(self.maxpool(x_256),2)        x_512 = torch.squeeze(self.maxpool(x_512),2)        x_1024 = torch.squeeze(self.maxpool(x_1024),2)        print(x_1024.shape)        L = [x_1024,x_512,x_256,x_128]        x = torch.cat(L,1)        print(x.shape)        return x

• 输出各阶段预测点，还考虑骨骼之间的关系
  

分层预测

PF-Net分层预测代码实现如下：

def forward(self,x):        print(np.array(x).shape)        x = self.latentfeature(x)        print(x.shape)        x_1 = F.relu(self.fc1(x)) #1024        print(x_1.shape)        x_2 = F.relu(self.fc2(x_1)) #512        print(x_2.shape)        x_3 = F.relu(self.fc3(x_2))  #256        print(x_3.shape)                        pc1_feat = self.fc3_1(x_3)        print(pc1_feat.shape)        pc1_xyz = pc1_feat.reshape(-1,64,3) #64x3 center1        print(pc1_xyz.shape)                pc2_feat = F.relu(self.fc2_1(x_2))        print(pc2_feat.shape)        pc2_feat = pc2_feat.reshape(-1,128,64)        print(pc2_feat.shape)        pc2_xyz =self.conv2_1(pc2_feat) #6x64 center2        print(pc2_xyz.shape)                pc3_feat = F.relu(self.fc1_1(x_1))        print(pc3_feat.shape)        pc3_feat = pc3_feat.reshape(-1,512,128)        print(pc3_feat.shape)        pc3_feat = F.relu(self.conv1_1(pc3_feat))        print(pc3_feat.shape)        pc3_feat = F.relu(self.conv1_2(pc3_feat))        print(pc3_feat.shape)        pc3_xyz = self.conv1_3(pc3_feat) #12x128 fine        print(pc3_xyz.shape)                pc1_xyz_expand = torch.unsqueeze(pc1_xyz,2)        print(pc1_xyz_expand.shape)        pc2_xyz = pc2_xyz.transpose(1,2)        print(pc2_xyz.shape)        pc2_xyz = pc2_xyz.reshape(-1,64,2,3)        print(pc2_xyz.shape)        pc2_xyz = pc1_xyz_expand+pc2_xyz        print(pc2_xyz.shape)        pc2_xyz = pc2_xyz.reshape(-1,128,3)         print(pc2_xyz.shape)                pc2_xyz_expand = torch.unsqueeze(pc2_xyz,2)        print(pc2_xyz_expand.shape)        pc3_xyz = pc3_xyz.transpose(1,2)        print(pc3_xyz.shape)        pc3_xyz = pc3_xyz.reshape(-1,128,int(self.crop_point_num/128),3)        print(pc3_xyz.shape)        pc3_xyz = pc2_xyz_expand+pc3_xyz        print(pc3_xyz.shape)        pc3_xyz = pc3_xyz.reshape(-1,self.crop_point_num,3)         print(pc3_xyz.shape)                return pc1_xyz,pc2_xyz,pc3_xyz #center1 ,center2 ,fine

Chamfer Distance

• Chamfer Distance来衡量预测效果与GT之间的差异
  

GAN

• 整体架构还是GAN形式
  

BCELoss损失模块

BCELoss模块代码实现如下:

import mathr11 = 0 * math.log(0.8707) + (1-0) * math.log((1 - 0.8707))r12 = 1 * math.log(0.7517) + (1-1) * math.log((1 - 0.7517))r13 = 1 * math.log(0.8162) + (1-1) * math.log((1 - 0.8162))r21 = 1 * math.log(0.3411) + (1-1) * math.log((1 - 0.3411))r22 = 1 * math.log(0.4872) + (1-1) * math.log((1 - 0.4872))r23 = 1 * math.log(0.6815) + (1-1) * math.log((1 - 0.6815))r31 = 0 * math.log(0.4847) + (1-0) * math.log((1 - 0.4847))r32 = 0 * math.log(0.6589) + (1-0) * math.log((1 - 0.6589))r33 = 0 * math.log(0.5273) + (1-0) * math.log((1 - 0.5273))r1 = -(r11 + r12 + r13) / 3#0.8447112733378236r2 = -(r21 + r22 + r23) / 3#0.7260397266631787r3 = -(r31 + r32 + r33) / 3#0.8292933181294807bceloss = (r1 + r2 + r3) / 3 print(bceloss)

判别模块代码实现如下：

 def forward(self, x):        x = F.relu(self.bn1(self.conv1(x)))        x_64 = F.relu(self.bn2(self.conv2(x)))        x_128 = F.relu(self.bn3(self.conv3(x_64)))        x_256 = F.relu(self.bn4(self.conv4(x_128)))        x_64 = torch.squeeze(self.maxpool(x_64))        x_128 = torch.squeeze(self.maxpool(x_128))        x_256 = torch.squeeze(self.maxpool(x_256))        Layers = [x_256,x_128,x_64]        x = torch.cat(Layers,1)        x = F.relu(self.bn_1(self.fc1(x)))        x = F.relu(self.bn_2(self.fc2(x)))        x = F.relu(self.bn_3(self.fc3(x)))        x = self.fc4(x)        return x

点云补全项目应用

如果需要本文完整代码，以上算法论文或者点云数据资源的小伙伴可以私信我哦！

来源地址：https://blog.csdn.net/denny_data/article/details/129472080