Skip to main content

2016 | OriginalPaper | Buchkapitel

Two-Stage Convolutional Part Heatmap Regression for the 1st 3D Face Alignment in the Wild (3DFAW) Challenge

verfasst von : Adrian Bulat, Georgios Tzimiropoulos

Erschienen in: Computer Vision – ECCV 2016 Workshops

Verlag: Springer International Publishing

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

This paper describes our submission to the 1st 3D Face Alignment in the Wild (3DFAW) Challenge. Our method builds upon the idea of convolutional part heatmap regression (Bulat and Tzimiropoulos, 2016), extending it for 3D face alignment. Our method decomposes the problem into two parts: (a) X,Y (2D) estimation and (b) Z (depth) estimation. At the first stage, our method estimates the X,Y coordinates of the facial landmarks by producing a set of 2D heatmaps, one for each landmark, using convolutional part heatmap regression. Then, these heatmaps, alongside the input RGB image, are used as input to a very deep subnetwork trained via residual learning for regressing the Z coordinate. Our method ranked 1st in the 3DFAW Challenge, surpassing the second best result by more than 22 %. Code can be found at http://​www.​cs.​nott.​ac.​uk/​~psxab5/​.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literatur
1.
Zurück zum Zitat Cao, X., Wei, Y., Wen, F., Sun, J.: Face alignment by explicit shape regression. In: CVPR (2012) Cao, X., Wei, Y., Wen, F., Sun, J.: Face alignment by explicit shape regression. In: CVPR (2012)
2.
Zurück zum Zitat Xiong, X., De la Torre, F.: Supervised descent method and its applications to face alignment. In: CVPR, pp. 532–539(2013) Xiong, X., De la Torre, F.: Supervised descent method and its applications to face alignment. In: CVPR, pp. 532–539(2013)
3.
Zurück zum Zitat Sagonas, C., Tzimiropoulos, G., Zafeiriou, S., Pantic, M.: A semi-automatic methodology for facial landmark annotation. In: CVPR-W (2013) Sagonas, C., Tzimiropoulos, G., Zafeiriou, S., Pantic, M.: A semi-automatic methodology for facial landmark annotation. In: CVPR-W (2013)
4.
Zurück zum Zitat Sagonas, C., Tzimiropoulos, G., Zafeiriou, S., Pantic, M.: 300 faces in-the-wild challenge: the first facial landmark localization challenge. In: CVPR, pp. 397–403 (2013) Sagonas, C., Tzimiropoulos, G., Zafeiriou, S., Pantic, M.: 300 faces in-the-wild challenge: the first facial landmark localization challenge. In: CVPR, pp. 397–403 (2013)
5.
Zurück zum Zitat Shen, J., Zafeiriou, S., Chrysos, G., Kossaifi, J., Tzimiropoulos, G., Pantic, M.: The first facial landmark tracking in-the-wild challenge: benchmark and results. In: ICCV-W (2015) Shen, J., Zafeiriou, S., Chrysos, G., Kossaifi, J., Tzimiropoulos, G., Pantic, M.: The first facial landmark tracking in-the-wild challenge: benchmark and results. In: ICCV-W (2015)
6.
Zurück zum Zitat Jourabloo, A., Liu, X.: Pose-invariant 3D face alignment. In: CVPR, pp. 3694–3702 (2015) Jourabloo, A., Liu, X.: Pose-invariant 3D face alignment. In: CVPR, pp. 3694–3702 (2015)
7.
Zurück zum Zitat Jourabloo, A., Liu, X.: Large-pose face alignment via CNN-based dense 3D model fitting. In: CVPR (2016) Jourabloo, A., Liu, X.: Large-pose face alignment via CNN-based dense 3D model fitting. In: CVPR (2016)
8.
Zurück zum Zitat Zhu, S., Li, C., Change Loy, C., Tang, X.: Face alignment by coarse-to-fine shape searching. In: CVPR, pp. 4998–5006 (2015) Zhu, S., Li, C., Change Loy, C., Tang, X.: Face alignment by coarse-to-fine shape searching. In: CVPR, pp. 4998–5006 (2015)
9.
Zurück zum Zitat Bulat, A., Tzimiropoulos, G.: Convolutional aggregation of local evidence for large pose face alignment. In: BMVC (2016) Bulat, A., Tzimiropoulos, G.: Convolutional aggregation of local evidence for large pose face alignment. In: BMVC (2016)
11.
12.
13.
Zurück zum Zitat Bulat, A., Tzimiropoulos, G.: Human pose estimation via convolutional part heatmap regression. In: ECCV (2016) Bulat, A., Tzimiropoulos, G.: Human pose estimation via convolutional part heatmap regression. In: ECCV (2016)
14.
Zurück zum Zitat Zeiler, M.D., Taylor, G.W., Fergus, R.: Adaptive deconvolutional networks for mid and high level feature learning. In: ICCV, pp. 2018–2025. IEEE (2011) Zeiler, M.D., Taylor, G.W., Fergus, R.: Adaptive deconvolutional networks for mid and high level feature learning. In: ICCV, pp. 2018–2025. IEEE (2011)
15.
16.
Zurück zum Zitat Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR, pp. 3431–3440 (2015) Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR, pp. 3431–3440 (2015)
17.
Zurück zum Zitat Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: A large-scale hierarchical image database. In: CVPR, pp. 248–255. IEEE (2009) Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: A large-scale hierarchical image database. In: CVPR, pp. 248–255. IEEE (2009)
18.
Zurück zum Zitat Collobert, R., Kavukcuoglu, K., Farabet, C.: Torch7: A matlab-like environment for machine learning. In: NIPS-W. Number EPFL-CONF-192376 (2011) Collobert, R., Kavukcuoglu, K., Farabet, C.: Torch7: A matlab-like environment for machine learning. In: NIPS-W. Number EPFL-CONF-192376 (2011)
19.
Zurück zum Zitat Gross, R., Matthews, I., Cohn, J., Kanade, T., Baker, S.: Multi-pie. Image Vis. Comput. 28(5), 807–813 (2010)CrossRef Gross, R., Matthews, I., Cohn, J., Kanade, T., Baker, S.: Multi-pie. Image Vis. Comput. 28(5), 807–813 (2010)CrossRef
20.
Zurück zum Zitat Yin, L., Chen, X., Sun, Y., Worm, T., Reale, M.: A high-resolution 3D dynamic facial expression database. In: 8th IEEE International Conference on Automatic Face & Gesture Recognition, FG 2008, pp. 1–6. IEEE (2008) Yin, L., Chen, X., Sun, Y., Worm, T., Reale, M.: A high-resolution 3D dynamic facial expression database. In: 8th IEEE International Conference on Automatic Face & Gesture Recognition, FG 2008, pp. 1–6. IEEE (2008)
21.
Zurück zum Zitat Zhang, X., Yin, L., Cohn, J.F., Canavan, S., Reale, M., Horowitz, A., Liu, P., Girard, J.M.: BP4D-spontaneous: a high-resolution spontaneous 3D dynamic facial expression database. Image Vis. Comput. 32(10), 692–706 (2014)CrossRef Zhang, X., Yin, L., Cohn, J.F., Canavan, S., Reale, M., Horowitz, A., Liu, P., Girard, J.M.: BP4D-spontaneous: a high-resolution spontaneous 3D dynamic facial expression database. Image Vis. Comput. 32(10), 692–706 (2014)CrossRef
22.
Zurück zum Zitat Jeni, L.A., Cohn, J.F., Kanade, T.: Dense 3D face alignment from 2D video for real-time use. Image and Vision Computing (2016) Jeni, L.A., Cohn, J.F., Kanade, T.: Dense 3D face alignment from 2D video for real-time use. Image and Vision Computing (2016)
Metadaten
Titel
Two-Stage Convolutional Part Heatmap Regression for the 1st 3D Face Alignment in the Wild (3DFAW) Challenge
verfasst von
Adrian Bulat
Georgios Tzimiropoulos
Copyright-Jahr
2016
DOI
https://doi.org/10.1007/978-3-319-48881-3_43