BriefGPT.xyz
Aug, 2018
通过对抗训练重新思考单目深度估计
Rethinking Monocular Depth Estimation with Adversarial Training
HTML
PDF
Richard Chen, Faisal Mahmood, Alan Yuille, Nicholas J. Durr
TL;DR
该研究利用对抗训练方法实现单目深度估计，通过引入上下文感知的非局部损失函数，将深度值的预测作为一个整体进行惩罚，具有较好的性能表现。
Abstract
monocular depth estimation
is an extensively studied computer vision problem with a vast variety of applications. This work introduces a novel paradigm for
monocular depth estimation
using deep networks that inco
→