Dilated Fully Convolutional Neural Network for Depth Estimation from a Single Image

by   Binghan Li, et al.

Depth prediction plays a key role in understanding a 3D scene. Several techniques have been developed throughout the years, among which Convolutional Neural Network has recently achieved state-of-the-art performance on estimating depth from a single image. However, traditional CNNs suffer from the lower resolution and information loss caused by the pooling layers. And oversized parameters generated from fully connected layers often lead to a exploded memory usage problem. In this paper, we present an advanced Dilated Fully Convolutional Neural Network to address the deficiencies. Taking advantages of the exponential expansion of the receptive field in dilated convolutions, our model can minimize the loss of resolution. It also reduces the amount of parameters significantly by replacing the fully connected layers with the fully convolutional layers. We show experimentally on NYU Depth V2 datasets that the depth prediction obtained from our model is considerably closer to ground truth than that from traditional CNNs techniques.


page 2

page 6


Incorporating Depth into both CNN and CRF for Indoor Semantic Segmentation

To improve segmentation performance, a novel neural network architecture...

Dealing with Topological Information within a Fully Convolutional Neural Network

A fully convolutional neural network has a receptive field of limited si...

Depth from Monocular Images using a Semi-Parallel Deep Neural Network (SPDNN) Hybrid Architecture

Convolutional Neural Network (CNN) techniques are applied to the problem...

Direction of Arrival Estimation of Sound Sources Using Icosahedral CNNs

In this paper, we present a new model for Direction of Arrival (DOA) est...

Fully-Convolutional Intensive Feature Flow Neural Network for Text Recognition

The Deep Convolutional Neural Networks (CNNs) have obtained a great succ...

Size Matters

Fully convolutional neural networks can process input of arbitrary size ...

Please sign up or login with your details

Forgot password? Click here to reset