论文标题
Squeezesegv3：在空间自适应卷积上，用于有效的点云分段
SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation
论文作者
论文摘要
激光点云分段是许多应用程序的重要问题。对于大规模点云进行分割，\ textit {de facto}方法是投影3D点云以获取2D激光镜像并使用卷积来处理它。尽管常规RGB和LiDAR图像之间的相似性，但我们发现LiDAR图像的特征分布在不同的图像位置发生了巨大变化。使用标准卷积处理此类LiDAR图像是有问题的，因为卷积过滤器拾取了仅在图像中特定区域中活跃的本地特征。结果，网络的容量被详细阐述，分割性能降低。为了解决这个问题，我们建议根据输入图像为不同位置采用不同的过滤器。可以有效地计算SAC，因为它可以作为一系列元素乘法，IM2COL和标准卷积实现。这是一个一般框架，因此可以将几种先前的方法视为SAC的特殊情况。使用SAC，我们在Semantickitti基准测试中构建了用于LIDAR点云进行分割的SqueezeseGV3，并以可比的推理速度在Semantickitti基准上均以至少3.7％MIOU的速度优于所有先前发布的方法。
LiDAR point-cloud segmentation is an important problem for many applications. For large-scale point cloud segmentation, the \textit{de facto} method is to project a 3D point cloud to get a 2D LiDAR image and use convolutions to process it. Despite the similarity between regular RGB and LiDAR images, we discover that the feature distribution of LiDAR images changes drastically at different image locations. Using standard convolutions to process such LiDAR images is problematic, as convolution filters pick up local features that are only active in specific regions in the image. As a result, the capacity of the network is under-utilized and the segmentation performance decreases. To fix this, we propose Spatially-Adaptive Convolution (SAC) to adopt different filters for different locations according to the input image. SAC can be computed efficiently since it can be implemented as a series of element-wise multiplications, im2col, and standard convolution. It is a general framework such that several previous methods can be seen as special cases of SAC. Using SAC, we build SqueezeSegV3 for LiDAR point-cloud segmentation and outperform all previous published methods by at least 3.7% mIoU on the SemanticKITTI benchmark with comparable inference speed.
