Deeper Depth Prediction with Fully Convolutional Residual Networks

TL;DR

This paper introduces a fully convolutional residual network for monocular depth estimation that improves resolution learning, uses a novel loss function, and achieves real-time performance with fewer parameters and better accuracy.

Contribution

It presents a novel end-to-end deep learning architecture with efficient up-sampling and a new loss function for improved monocular depth prediction.

Findings

Outperforms existing methods on depth estimation benchmarks.

Operates in real-time without post-processing.

Uses fewer parameters and training data than prior models.

Abstract

This paper addresses the problem of estimating the depth map of a scene given a single RGB image. We propose a fully convolutional architecture, encompassing residual learning, to model the ambiguous mapping between monocular images and depth maps. In order to improve the output resolution, we present a novel way to efficiently learn feature map up-sampling within the network. For optimization, we introduce the reverse Huber loss that is particularly suited for the task at hand and driven by the value distributions commonly present in depth maps. Our model is composed of a single architecture that is trained end-to-end and does not rely on post-processing techniques, such as CRFs or other additional refinement steps. As a result, it runs in real-time on images or videos. In the evaluation, we show that the proposed model contains fewer parameters and requires fewer training data than the current state of the art, while outperforming all approaches on depth estimation. Code and models are publicly available.