Single image depth estimation by dilated deep residual convolutional neural network and soft-weight-sum inference
Single image depth estimation by dilated deep residual convolutional neural network and soft-weight-sum inference
复制标题
DOI：
--
复制
发表时间：
2017-04
期刊：
影响因子：
--
通讯作者：
Bo Li;Yuchao Dai;Huahui Chen;Mingyi He
中科院分区：
文献类型：
--
作者：
Bo Li;Yuchao Dai;Huahui Chen;Mingyi He
本文提出了一种用于单图像深度估计的新残差卷积神经网络（CNN）架构。与现有的基于深度 CNN 的方法相比，我们的方法用更少的训练样本和模型参数取得了更好的结果。我们的方法的优点来自于扩张卷积、跳跃连接架构和软权重和推理的使用。对 NYU Depth V2 数据集的实验评估表明，我们的方法明显优于其他最先进的方法。
This paper proposes a new residual convolutional neural network (CNN) architecture for single image depth estimation. Compared with existing deep CNN based methods, our method achieves much better results with fewer training examples and model parameters. The advantages of our method come from the usage of dilated convolution, skip connection architecture and soft-weight-sum inference. Experimental evaluation on the NYU Depth V2 dataset shows that our method outperforms other state-of-the-art methods by a margin.