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
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.
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