Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Sign Up
Cited by 1,982

The DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index.

Deeper Depth Prediction with Fully Convolutional Residual Networks

Open access
Laina, Iro, Rupprecht, Christian, Belagiannis, Vasileios, Tombari, Federico, Navab, Nassir·2016·2016 Fourth International Conference on 3D Vision (3DV)
DOI 10.1109/3dv.2016.32
Open this paper in CoChat — free account

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.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/3dv.2016.32

Cites

6 of 6 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 34

  1. 10.1109/34.784284 · DOI · Paper page
  2. 10.1109/ICCV.2011.6126474 · DOI · Paper page
  3. 10.1109/CVPR.2015.7298972 · DOI · Paper page
  4. 10.1007/978-3-540-28649-3_30 · DOI
  5. simonyan, 2014, Very Deep Convolutional Networks for Large-scale Image Recognition
  6. 10.1109/TPAMI.2008.132 · DOI · Paper page
  7. 10.1109/CVPR.2015.7298897 · DOI · Paper page
  8. vedaldi, 2015, Matconvnet - convolutional neural networks for matlab
  9. 10.1109/CVPR.2012.6247664 · DOI · Paper page
  10. 10.1007/978-1-84882-935-0_7 · doi:10.1007/978-1-84882-935-0_7
  11. karsch, 2012, Depth extraction from video using non-parametric sampling, Proc Europ Conf Computer Vision (ECCV), 775
  12. zwald, 2012, The berhu penalty and the grouped effect
  13. 10.1109/3DV.2013.9 · DOI · Paper page
  14. 10.1109/ICRA.2013.6631104 · DOI · Paper page
  15. 10.1109/CVPRW.2012.6238903 · DOI
  16. krizhevsky, 2012, Imagenet classification with deep convolutional neural networks, Advances in neural information processing systems, 1097
  17. 10.1109/CVPR.2014.19 · DOI · Paper page
  18. li, 2015, Depth and surface normal estimation from monocular images using regression on deep features and hierarchical CRFs, Proc Conf Computer Vision and Pattern Recognition (CVPR), 1119
  19. 10.1109/CVPR.2010.5539823 · DOI · Paper page
  20. 10.1109/TPAMI.2010.147 · DOI · Paper page
  21. 10.1109/CVPR.2015.7299152 · DOI · Paper page
  22. 10.1109/CVPR.2015.7298761 · DOI · Paper page
  23. 10.1109/CVPR.2016.594 · DOI · Paper page
  24. eigen, 2014, Prediction from a single image using a multi-scale deep network, Proc Conf Neural Information Processing Systems (NIPS)
  25. saxena, 2005, Learning depth from single monocular images, Advances in neural information processing systems, 1161
  26. 10.1109/ICCV.2015.304 · DOI · Paper page
  27. 10.1109/ICCV.2005.107 · DOI · Paper page
  28. 10.1109/ICCV.2015.324 · DOI
  29. 10.1109/TPAMI.2012.120 · DOI · Paper page
  30. memisevic, 2011, Stereopsis via deep learning, NIPS Workshop on Deep Learning, 1
  31. 10.1109/CVPR.2015.7298965 · DOI · Paper page
  32. oliva, 2014, Modeling the shape of the scene: A holistic representation of the spatial envelope, Int Journal of Computer Vision (IJCV), 145
  33. ren, 2012, Rgb-(d) scene labeling: Features and algorithms, Computer Vision and Pattern Recognition (CVPR) 2012 IEEE Conference on, 2759
  34. 10.1090/conm/443/08555 · DOI · Paper page

Cited by

See all 1,982

Metadata

Authors
Laina, I., Rupprecht, C., Belagiannis, V., Tombari, F., & Navab, N.
Venue
2016 Fourth International Conference on 3D Vision (3DV)
Publisher
IEEE
Published
2016-10
Pages
239-248
DOI
10.1109/3dv.2016.32
OpenAlex
W2409352305
Cited by
1,982
References
6
FWCI
60.38
Type
conference paper
Language
en
Open access
green

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.