Single image depth estimation by dilated deep residual convolutional neural network and soft-weight-sum inference
This work addresses depth estimation from single images, a key problem in computer vision, with incremental improvements in efficiency and performance.
The paper tackles single image depth estimation by proposing a new residual CNN architecture that uses dilated convolution, skip connections, and soft-weight-sum inference, achieving better results with fewer training examples and parameters, as shown by outperforming state-of-the-art methods on the NYU Depth V2 dataset.
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.