SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation

TL;DR

SqueezeSegV3 introduces Spatially-Adaptive Convolution (SAC) to improve LiDAR point-cloud segmentation by adapting filters to local feature distributions, leading to significant performance gains over previous methods.

Contribution

The paper proposes SAC, a general and efficient convolution method that adapts filters spatially, and applies it in SqueezeSegV3 to outperform existing LiDAR segmentation approaches.

Findings

Achieved at least 3.7% higher mIoU on SemanticKITTI benchmark.

SAC can be implemented efficiently with standard operations.

SqueezeSegV3 maintains comparable inference speed to prior methods.

Abstract

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.