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

04/03/2020
by   Chenfeng Xu, et al.
4

LiDAR point-cloud segmentation is an important problem for many applications. For large-scale point cloud segmentation, the 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 benchmark with comparable inference speed.

READ FULL TEXT

page 3

page 7

11/19/2020

Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation

State-of-the-art methods for large-scale driving-scene LiDAR segmentatio...
11/30/2021

Semi-Local Convolutions for LiDAR Scan Processing

A number of applications, such as mobile robots or automated vehicles, u...
09/12/2021

Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR-based Perception

State-of-the-art methods for driving-scene LiDAR-based perception (inclu...
02/25/2020

FPConv: Learning Local Flattening for Point Convolution

We introduce FPConv, a novel surface-style convolution operator designed...
06/14/2021

PolarStream: Streaming Lidar Object Detection and Segmentation with Polar Pillars

Recent works recognized lidars as an inherently streaming data source an...
06/23/2020

Efficient Spatially Adaptive Convolution and Correlation

Fast methods for convolution and correlation underlie a variety of appli...
01/23/2018

PointCNN

We present a simple and general framework for feature learning from poin...