pointnet和pointnet++

最新推荐文章于 2025-05-26 15:47:25 发布

原创

最新推荐文章于 2025-05-26 15:47:25 发布 · 5.9k 阅读

11 ·

CC 4.0 BY-SA版权

PointNet和PointNet++是用于点云处理的深度学习模型，主要应用于点云分类和分割任务。PointNet通过T-net进行空间变换，通过max pool获取全局特征。然而，它忽略了局部信息，不适合处理多实例分类问题。PointNet++引入set abstraction和feature propagation，考虑了局部结构，提高了处理能力。在分割任务中，PointNet++借鉴了DSSD的框架，通过Feature Propagation layers结合高层和低层特征。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

pointnet++是pointnet的改进版本，两者都可以做点云分类和点云分割
代码：pointnet系列

pointnet：

分类：
这里写图片描述
输入：B*N*（d+C） d为坐标xyz,C为点属性（在modelnet40数据集没有点属性）图中为B*N*3
transform:通过T-net得到B*3*3的变换矩阵，对坐标进空间变换
mlp:相当于1*1的卷积
max pool:获取全局特征
输出：k个分类

def get_model(point_cloud, is_training, bn_decay=None):

    """ Classification PointNet, input is BxNx3, output Bx40 """

    batch_size = point_cloud.get_shape()[0].value

    num_point = point_cloud.get_shape()[1].value

    end_points = {}



    with tf.variable_scope('transform_net1') as sc:

        transform = input_transform_net(point_cloud, is_training, bn_decay, K=3)

    point_cloud_transformed = tf.matmul(point_cloud, transform)

    input_image = tf.expand_dims(point_cloud_transformed, -1)



    net = tf_util.conv2d(input_image, 64, [1,3],

                         padding='VALID', stride=[1,1],

                         bn=True, is_training=is_training,

                         scope='conv1', bn_decay=bn_decay)

    net = tf_util.conv2d(net, 64, [1,1],

                         padding='VALID', stride=[1,1],

                         bn=True, is_training=is_training,

                         scope='conv2', bn_decay=bn_decay)



    with tf.variable_scope('transform_net2') as sc:

        transform = feature_transform_net(net, is_training, bn_decay, K=64)

    end_points['transform'] = transform

    net_transformed = tf.matmul(tf.squeeze(net, axis=[2]), transform)

    net_transformed = tf.expand_dims(net_transformed, [2])



    net = tf_util.conv2d(net_transformed, 64, [1,1],

                         padding='VALID', stride=[1,1],

                         bn=True, is_training=is_training,

                         scope='conv3', bn_decay=bn_decay)

    net = tf_util.conv2d(net, 128, [1,1],

                         padding='VALID', stride=[1,1],

                         bn=True, is_training=is_training,

                         scope='conv4', bn_decay=bn_decay)

    net = tf_util.conv2d(net, 1024, [1,1],

                         padding='VALID', stride=[1,1],

                         bn=True, is_training=is_training,

                         scope='conv5', bn_decay=bn_decay)



    # Symmetric function: max pooling

    net = tf_util.max_pool2d(net, [num_point,1],

                             padding='VALID', scope='maxpool')



    net = tf.reshape(net, [batch_size, -1])

    net = tf_util.fully_connected(net, 512, bn=True, is_training=is_training,

                                  scope='fc1', bn_decay=bn_decay)

    net = tf_util.dropout(net, keep_prob=0.7, is_training=is_training,

                          scope='dp1')

    net = tf_util.fully_connected(net, 256<