Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture

David Eigen, Robert Fergus

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper we address three different computer vision tasks using a single basic architecture: depth prediction, surface normal estimation, and semantic labeling. We use a multiscale convolutional network that is able to adapt easily to each task using only small modifications, regressing from the input image to the output map directly. Our method progressively refines predictions using a sequence of scales, and captures many image details without any superpixels or low-level segmentation. We achieve state-of-the-art performance on benchmarks for all three tasks.

Original languageEnglish (US)
Title of host publicationProceedings - 2015 IEEE International Conference on Computer Vision, ICCV 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2650-2658
Number of pages9
Volume11-18-December-2015
ISBN (Electronic)9781467383912
DOIs
StatePublished - Feb 17 2016
Event15th IEEE International Conference on Computer Vision, ICCV 2015 - Santiago, Chile
Duration: Dec 11 2015Dec 18 2015

Other

Other15th IEEE International Conference on Computer Vision, ICCV 2015
CountryChile
CitySantiago
Period12/11/1512/18/15

Fingerprint

Labels
Semantics
Labeling
Computer vision

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Eigen, D., & Fergus, R. (2016). Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture. In Proceedings - 2015 IEEE International Conference on Computer Vision, ICCV 2015 (Vol. 11-18-December-2015, pp. 2650-2658). [7410661] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCV.2015.304

Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture. / Eigen, David; Fergus, Robert.

Proceedings - 2015 IEEE International Conference on Computer Vision, ICCV 2015. Vol. 11-18-December-2015 Institute of Electrical and Electronics Engineers Inc., 2016. p. 2650-2658 7410661.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Eigen, D & Fergus, R 2016, Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture. in Proceedings - 2015 IEEE International Conference on Computer Vision, ICCV 2015. vol. 11-18-December-2015, 7410661, Institute of Electrical and Electronics Engineers Inc., pp. 2650-2658, 15th IEEE International Conference on Computer Vision, ICCV 2015, Santiago, Chile, 12/11/15. https://doi.org/10.1109/ICCV.2015.304
Eigen D, Fergus R. Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture. In Proceedings - 2015 IEEE International Conference on Computer Vision, ICCV 2015. Vol. 11-18-December-2015. Institute of Electrical and Electronics Engineers Inc. 2016. p. 2650-2658. 7410661 https://doi.org/10.1109/ICCV.2015.304
Eigen, David ; Fergus, Robert. / Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture. Proceedings - 2015 IEEE International Conference on Computer Vision, ICCV 2015. Vol. 11-18-December-2015 Institute of Electrical and Electronics Engineers Inc., 2016. pp. 2650-2658
@inproceedings{08726940aabe428ba05e4cbdfefcb0d7,
title = "Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture",
abstract = "In this paper we address three different computer vision tasks using a single basic architecture: depth prediction, surface normal estimation, and semantic labeling. We use a multiscale convolutional network that is able to adapt easily to each task using only small modifications, regressing from the input image to the output map directly. Our method progressively refines predictions using a sequence of scales, and captures many image details without any superpixels or low-level segmentation. We achieve state-of-the-art performance on benchmarks for all three tasks.",
author = "David Eigen and Robert Fergus",
year = "2016",
month = "2",
day = "17",
doi = "10.1109/ICCV.2015.304",
language = "English (US)",
volume = "11-18-December-2015",
pages = "2650--2658",
booktitle = "Proceedings - 2015 IEEE International Conference on Computer Vision, ICCV 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

TY - GEN

T1 - Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture

AU - Eigen, David

AU - Fergus, Robert

PY - 2016/2/17

Y1 - 2016/2/17

N2 - In this paper we address three different computer vision tasks using a single basic architecture: depth prediction, surface normal estimation, and semantic labeling. We use a multiscale convolutional network that is able to adapt easily to each task using only small modifications, regressing from the input image to the output map directly. Our method progressively refines predictions using a sequence of scales, and captures many image details without any superpixels or low-level segmentation. We achieve state-of-the-art performance on benchmarks for all three tasks.

AB - In this paper we address three different computer vision tasks using a single basic architecture: depth prediction, surface normal estimation, and semantic labeling. We use a multiscale convolutional network that is able to adapt easily to each task using only small modifications, regressing from the input image to the output map directly. Our method progressively refines predictions using a sequence of scales, and captures many image details without any superpixels or low-level segmentation. We achieve state-of-the-art performance on benchmarks for all three tasks.

UR - http://www.scopus.com/inward/record.url?scp=84973897611&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84973897611&partnerID=8YFLogxK

U2 - 10.1109/ICCV.2015.304

DO - 10.1109/ICCV.2015.304

M3 - Conference contribution

VL - 11-18-December-2015

SP - 2650

EP - 2658

BT - Proceedings - 2015 IEEE International Conference on Computer Vision, ICCV 2015

PB - Institute of Electrical and Electronics Engineers Inc.

ER -