BriefGPT.xyz
Mar, 2021
$S^3$: 可学习的稀疏信号超密度用于引导深度估计
$S^3$: Learnable Sparse Signal Superdensity for Guided Depth Estimation
HTML
PDF
Yu-Kai Huang, Yueh-Cheng Liu, Tsung-Han Wu, Hung-Ting Su, Yu-Cheng Chang...
TL;DR
本文提出了一种名为S3技术的新方法，支持在体积形成的不同阶段进行端到端的训练，并可将其应用于LiDAR和雷达信号上，以优化稀疏信号的利用，提高密集深度估计的精确度和可靠性。
Abstract
dense depth estimation
plays a key role in multiple applications such as robotics, 3D reconstruction, and augmented reality. While sparse signal, e.g.,
lidar
and
→