Recent learning-based LiDAR odometry methods have demonstrated their
competitiveness. However, most methods still face two substantial challenges:
1) the 2D projection representation of LiDAR data cannot effectively encode 3D
structures from the point clouds; 2) the needs for a large amount of labeled
data for training limit the application scope of these methods. In this paper,
we propose a self-supervised LiDAR odometry method, dubbed SelfVoxeLO, to
tackle these two difficulties. Specifically, we propose a 3D convolution
network to process the raw LiDAR data directly, which extracts features that
better encode the 3D geometric patterns. To suit our network to self-supervised
learning, we design several novel loss functions that utilize the inherent
properties of LiDAR point clouds. Moreover, an uncertainty-aware mechanism is
incorporated in the loss functions to alleviate the interference of moving
objects/noises. We evaluate our method's performances on two large-scale
datasets, i.e., KITTI and Apollo-SouthBay. Our method outperforms
state-of-the-art unsupervised methods by 27%/32% in terms of
translational/rotational errors on the KITTI dataset and also performs well on
the Apollo-SouthBay dataset. By including more unlabelled training data, our
method can further improve performance comparable to the supervised methods.

本文提出了一种自监督的 LiDAR 测距法 ——SelfVoxeLO，通过使用 3D 卷积网络对点云数据进行特征提取，利用 LiDAR 点云的内在属性设计了多种新颖的损失函数，并引入了一种不确定性感知的机制来减轻运动物体 / 噪声的干扰，该方法在 KITTI 和 Apollo-SouthBay 数据集上的性能超过了现有的无监督方法，并且可以通过添加更多未标记的训练数据来进一步提高性能，可与有监督的方法相媲美。

SelfVoxeLO: 使用基于体素深度神经网络的自监督 LiDAR 里程计

SelfVoxeLO: Self-supervised LiDAR Odometry with Voxel-based Deep Neural  Networks

We address the problem of spatio-temporal action detection in videos.
Existing methods commonly either ignore temporal context in action recognition
and localization, or lack the modelling of flexible shapes of action tubes. In
this paper, we propose a two-stage action detector called Deformable Tube
Network (DTN), which is composed of a Deformation Tube Proposal Network (DTPN)
and a Deformable Tube Recognition Network (DTRN) similar to the Faster R-CNN
architecture. In DTPN, a fast proposal linking algorithm (FTL) is introduced to
connect region proposals across frames to generate multiple deformable action
tube proposals. To perform action detection, we design a 3D convolution network
with skip connections for tube classification and regression. Modelling action
proposals as deformable tubes explicitly considers the shape of action tubes
compared to 3D cuboids. Moreover, 3D convolution based recognition network can
learn temporal dynamics sufficiently for action detection. Our experimental
results show that we significantly outperform the methods with 3D cuboids and
obtain the state-of-the-art results on both UCF-Sports and AVA datasets.

本研究提出了一种由 Deformation Tube Proposal Network（DTPN）和 Deformable Tube Recognition Network（DTRN）组成的 Deformable Tube Network，该网络能够对视频进行空间 - 时间动作检测，并通过建立动作的可变形管来检测动作。实验结果表明，与使用 3D cuboids 的方法相比，Deformable Tube Network 的性能显著提高，并在 UCF-Sports 和 AVA 数据集上获得了最先进的结果。