BriefGPT.xyz
Jun, 2016
使用全卷积残差网络进行更深的深度预测
Deeper Depth Prediction with Fully Convolutional Residual Networks
HTML
PDF
Iro Laina, Christian Rupprecht, Vasileios Belagiannis, Federico Tombari, Nassir Navab
TL;DR
采用残差学习和反Huber loss，提出了一种全卷积结构的模型，可通过单个RGB图像估计场景深度图，优于当前所有深度估计方法，且无需后处理技术，能够实时运行。
Abstract
This paper addresses the problem of estimating the
depth map
of a scene given a single RGB image. To model the ambiguous mapping between
monocular images
and depth maps, we leverage on deep learning capabilities
→