DeepAI
Log In Sign Up

CNN-based synthesis of realistic high-resolution LiDAR data

06/28/2019
by   Larissa T. Triess, et al.
0

This paper presents a novel CNN-based approach for synthesizing high-resolution LiDAR point cloud data. Our approach generates semantically and perceptually realistic results with guidance from specialized loss-functions. First, we utilize a modified per-point loss that addresses missing LiDAR point measurements. Second, we align the quality of our generated output with real-world sensor data by applying a perceptual loss. In large-scale experiments on real-world datasets, we evaluate both the geometric accuracy and semantic segmentation performance using our generated data vs. ground truth. In a mean opinion score testing we further assess the perceptual quality of our generated point clouds. Our results demonstrate a significant quantitative and qualitative improvement in both geometry and semantics over traditional non CNN-based up-sampling methods.

READ FULL TEXT

page 1

page 2

page 3

page 4

08/31/2022

A Realism Metric for Generated LiDAR Point Clouds

A considerable amount of research is concerned with the generation of re...
04/10/2020

Simulation-based Lidar Super-resolution for Ground Vehicles

We propose a methodology for lidar super-resolution with ground vehicles...
07/12/2021

SynLiDAR: Learning From Synthetic LiDAR Sequential Point Cloud for Semantic Segmentation

Transfer learning from synthetic to real data has been proved an effecti...
03/17/2022

AdaSplats: Adaptative Splats from Semantic Point Cloud for Fast and High-Fidelity LiDAR Simulation

LiDAR sensors provide rich 3D information about surrounding scenes and a...
06/17/2016

High-resolution LIDAR-based Depth Mapping using Bilateral Filter

High resolution depth-maps, obtained by upsampling sparse range data fro...
08/04/2022

Semantic Segmentation of Fruits on Multi-sensor Fused Data in Natural Orchards

Semantic segmentation is a fundamental task for agricultural robots to u...
07/27/2021

A persistent homology-based topological loss for CNN-based multi-class segmentation of CMR

Multi-class segmentation of cardiac magnetic resonance (CMR) images seek...