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

TL;DR

This paper introduces a dilated fully convolutional neural network that improves depth estimation from a single image by maintaining resolution and reducing parameters, outperforming traditional CNNs on NYU Depth V2 dataset.

Contribution

The paper proposes an advanced dilated fully convolutional neural network that addresses resolution loss and high parameter count in depth estimation models.

Findings

Model achieves closer depth predictions to ground truth.

Significantly reduces parameters compared to traditional CNNs.

Outperforms existing CNN techniques on NYU Depth V2 dataset.

Abstract

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.