Deeper depth prediction with fully convolutional residual networks

Laina I, Rupprecht C, Belagiannis V, Tombari F, Navab N (2016)

Publication Type: Conference contribution

Publication year: 2016

Publisher: Institute of Electrical and Electronics Engineers Inc.

Pages Range: 239-248

Conference Proceedings Title: Proceedings - 2016 4th International Conference on 3D Vision, 3DV 2016

Event location: Stanford, CA, USA

ISBN: 9781509054077

DOI: 10.1109/3DV.2016.32

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.

Authors with CRIS profile

Vasileios Belagiannis

Involved external institutions

Technische Universität München (TUM) DE Germany (DE) University of Oxford GB United Kingdom (GB)

How to cite

APA:

Laina, I., Rupprecht, C., Belagiannis, V., Tombari, F., & Navab, N. (2016). Deeper depth prediction with fully convolutional residual networks. In Proceedings - 2016 4th International Conference on 3D Vision, 3DV 2016 (pp. 239-248). Stanford, CA, USA: Institute of Electrical and Electronics Engineers Inc..

MLA:

Laina, Iro, et al. "Deeper depth prediction with fully convolutional residual networks." Proceedings of the 4th International Conference on 3D Vision, 3DV 2016, Stanford, CA, USA Institute of Electrical and Electronics Engineers Inc., 2016. 239-248.

BibTeX: Download