Most existing point cloud based 3D object detectors focus on the tasks of
classification and box regression. However, another bottleneck in this area is
achieving an accurate detection confidence for the Non-Maximum Suppression
(NMS) post-processing. In this paper, we add a 3D IoU prediction branch to the
regular classification and regression branches. The predicted IoU is used as
the detection confidence for NMS. In order to obtain a more accurate IoU
prediction, we propose a 3D IoU-Net with IoU sensitive feature learning and an
IoU alignment operation. To obtain a perspective-invariant prediction head, we
propose an Attentive Corner Aggregation (ACA) module by aggregating a local
point cloud feature from each perspective of eight corners and adaptively
weighting the contribution of each perspective with different attentions. We
propose a Corner Geometry Encoding (CGE) module for geometry information
embedding. To the best of our knowledge, this is the first time geometric
embedding information has been introduced in proposal feature learning. These
two feature parts are then adaptively fused by a multi-layer perceptron (MLP)
network as our IoU sensitive feature. The IoU alignment operation is introduced
to resolve the mismatching between the bounding box regression head and IoU
prediction, thereby further enhancing the accuracy of IoU prediction. The
experimental results on the KITTI car detection benchmark show that 3D IoU-Net
with IoU perception achieves state-of-the-art performance.

提出了一种在 3D 物体检测中通过 IoU 预测来解决 NMS 中准确性问题的方法，使用了 3D IoU-Net 进行特征学习和准确性预测，并通过 Corner Geometry Encoding 和 Attentive Corner Aggregation 模块提取几何信息并实现对预测角度的不变性，实验结果表明，该方法在 KITTI car detection benchmark 上达到了最先进水平。

3D IoU-Net: 基于 IoU 的点云三维物体检测器

3D IoU-Net: IoU Guided 3D Object Detector for Point Clouds

We present a generalized and scalable method, called Gen-LaneNet, to detect
3D lanes from a single image. The method, inspired by the latest
state-of-the-art 3D-LaneNet, is a unified framework solving image encoding,
spatial transform of features and 3D lane prediction in a single network.
However, we propose unique designs for Gen-LaneNet in two folds. First, we
introduce a new geometry-guided lane anchor representation in a new coordinate
frame and apply a specific geometric transformation to directly calculate real
3D lane points from the network output. We demonstrate that aligning the lane
points with the underlying top-view features in the new coordinate frame is
critical towards a generalized method in handling unfamiliar scenes. Second, we
present a scalable two-stage framework that decouples the learning of image
segmentation subnetwork and geometry encoding subnetwork. Compared to
3D-LaneNet, the proposed Gen-LaneNet drastically reduces the amount of 3D lane
labels required to achieve a robust solution in real-world application.
Moreover, we release a new synthetic dataset and its construction strategy to
encourage the development and evaluation of 3D lane detection methods. In
experiments, we conduct extensive ablation study to substantiate the proposed
Gen-LaneNet significantly outperforms 3D-LaneNet in average precision(AP) and
F-score.

介绍了一种基于 Gen-LaneNet 的 3D 车道检测方法，包括图像编码、特征空间变换、3D 车道预测、新的几何引导车道锚定表示法和可扩展的两阶段框架，同时推出了一个新的合成数据集。实验表明，该方法在平均精度（AP）和 F 分数方面明显优于 3D-LaneNet。