RandLA-Net Decoder

Decoder包括两部分:

• 最近邻插值
• 反卷积

f_decoder_list = []
    for j in range(self.config.num_layers):
        f_interp_i = self.nearest_interpolation(feature, inputs['interp_idx'][-j - 1])
        f_decoder_i = helper_tf_util.conv2d_transpose(tf.concat([f_encoder_list[-j - 2], f_interp_i], axis=3),
                                                          f_encoder_list[-j - 2].get_shape()[-1].value, [1, 1],
                                                          'Decoder_layer_' + str(j), [1, 1], 'VALID', bn=True,
                                                          is_training=is_training)
        feature = f_decoder_i
        f_decoder_list.append(f_decoder_i)

 

1. nearest_interpolation (最近邻插值):

与pointnet++ 不同, 这里的最近邻插值是用最近点的特征作为新点特征,

    def nearest_interpolation(feature, interp_idx):
        """
        :param feature: [B, N, d] input features matrix
        :param interp_idx: [B, up_num_points, 1] nearest neighbour index
        :return: [B, up_num_points, d] interpolated features matrix
        """
        feature = tf.squeeze(feature, axis=2)
        batch_size = tf.shape(interp_idx)[0]
        up_num_points = tf.shape(interp_idx)[1]
        interp_idx = tf.reshape(interp_idx, [batch_size, up_num_points])
        interpolated_features = tf.batch_gather(feature, interp_idx)
        interpolated_features = tf.expa

interp_idx 是当前点的最近邻索引, 在训练之前的准备数据阶段, 为各层生成采样点云时就用KNN记录了采样后的每个点云在采样前点云集中的最近邻点.即下面代码中的up_i.

   def get_tf_mapping(self):
        # Collect flat inputs
        def tf_map(batch_xyz, batch_features, batch_labels, batch_pc_idx, batch_cloud_idx):
            batch_features = tf.map_fn(self.tf_augment_input, [batch_xyz, batch_features], dtype=tf.float32)
            input_points = []
            input_neighbors = []
            input_pools = []
            input_up_samples = []

            for i in range(cfg.num_layers):
                neigh_idx = tf.py_func(DP.knn_search, [batch_xyz, batch_xyz, cfg.k_n], tf.int32)
                sub_points = batch_xyz[:, :tf.shape(batch_xyz)[1] // cfg.sub_sampling_ratio[i], :]
                pool_i = neigh_idx[:, :tf.shape(batch_xyz)[1] // cfg.sub_sampling_ratio[i], :]
                up_i = tf.py_func(DP.knn_search, [sub_points, batch_xyz, 1], tf.int32)
                input_points.append(batch_xyz)
                input_neighbors.append(neigh_idx)
                input_pools.append(pool_i)
                input_up_samples.append(up_i)
                batch_xyz = sub_points

            input_list = input_points + input_neighbors + input_pools + input_up_samples
            input_list += [batch_features, batch_labels, batch_pc_idx, batch_cloud_idx]

            return input_list

        return tf_map