Local Grid Rendering Networks for 3D Object Detection in Point Clouds

07/04/2020
by   Jianan Li, et al.
0

The performance of 3D object detection models over point clouds highly depends on their capability of modeling local geometric patterns. Conventional point-based models exploit local patterns through a symmetric function (e.g. max pooling) or based on graphs, which easily leads to loss of fine-grained geometric structures. Regarding capturing spatial patterns, CNNs are powerful but it would be computationally costly to directly apply convolutions on point data after voxelizing the entire point clouds to a dense regular 3D grid. In this work, we aim to improve performance of point-based models by enhancing their pattern learning ability through leveraging CNNs while preserving computational efficiency. We propose a novel and principled Local Grid Rendering (LGR) operation to render the small neighborhood of a subset of input points into a low-resolution 3D grid independently, which allows small-size CNNs to accurately model local patterns and avoids convolutions over a dense grid to save computation cost. With the LGR operation, we introduce a new generic backbone called LGR-Net for point cloud feature extraction with simple design and high efficiency. We validate LGR-Net for 3D object detection on the challenging ScanNet and SUN RGB-D datasets. It advances state-of-the-art results significantly by 5.5 and 4.5 mAP, respectively, with only slight increased computation overhead.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/25/2023

Improved Multi-Scale Grid Rendering of Point Clouds for Radar Object Detection Networks

Architectures that first convert point clouds to a grid representation a...
research
05/03/2022

Improved Orientation Estimation and Detection with Hybrid Object Detection Networks for Automotive Radar

This paper presents novel hybrid architectures that combine grid- and po...
research
11/19/2018

Modeling Local Geometric Structure of 3D Point Clouds using Geo-CNN

Recent advances in deep convolutional neural networks (CNNs) have motiva...
research
05/08/2023

PillarNeXt: Rethinking Network Designs for 3D Object Detection in LiDAR Point Clouds

In order to deal with the sparse and unstructured raw point clouds, LiDA...
research
11/30/2020

RfD-Net: Point Scene Understanding by Semantic Instance Reconstruction

Semantic scene understanding from point clouds is particularly challengi...
research
09/23/2021

Multi-resolution deep learning pipeline for dense large scale point clouds

Recent development of 3D sensors allows the acquisition of extremely den...
research
02/10/2020

Object condensation: one-stage grid-free multi-object reconstruction in physics detectors, graph and image data

High-energy physics detectors, images, and point clouds share many simil...

Please sign up or login with your details

Forgot password? Click here to reset