Unsupervised Geometry-Aware Representation for 3D Human Pose Estimation
Rhodin H, Salzmann M, Fua P (2018)
In: Computer Vision – ECCV 2018. 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part X. Ferrari V, Hebert M, Sminchisescu C, Weiss Y (Eds); Lecture Notes in Computer Science, 11214. Cham: Springer International Publishing: 765-782.
Sammelwerksbeitrag
| Veröffentlicht | Englisch
Download
Es wurden keine Dateien hochgeladen. Nur Publikationsnachweis!
Autor*in
Rhodin, HelgeUniBi ;
Salzmann, Mathieu;
Fua, Pascal
Herausgeber*in
Ferrari, Vittorio;
Hebert, Martial;
Sminchisescu, Cristian;
Weiss, Yair
Abstract / Bemerkung
Modern 3D human pose estimation techniques rely on deep networks, which require large amounts of training data. While weakly-supervised methods require less supervision, by utilizing 2D poses or multi-view imagery without annotations, they still need a sufficiently large set of samples with 3D annotations for learning to succeed.
In this paper, we propose to overcome this problem by learning a geometry-aware body representation from multi-view images without annotations. To this end, we use an encoder-decoder that predicts an image from one viewpoint given an image from another viewpoint. Because this representation encodes 3D geometry, using it in a semi-supervised setting makes it easier to learn a mapping from it to 3D human pose. As evidenced by our experiments, our approach significantly outperforms fully-supervised methods given the same amount of labeled data, and improves over other semi-supervised methods while using as little as 1% of the labeled data.
Erscheinungsjahr
2018
Buchtitel
Computer Vision – ECCV 2018. 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part X
Serientitel
Lecture Notes in Computer Science
Band
11214
Seite(n)
765-782
Konferenz
European Conference on Computer Vision
ISBN
978-3-030-01248-9
eISBN
978-3-030-01249-6
ISSN
0302-9743
eISSN
1611-3349
Page URI
https://pub.uni-bielefeld.de/record/2991927
Zitieren
Rhodin H, Salzmann M, Fua P. Unsupervised Geometry-Aware Representation for 3D Human Pose Estimation. In: Ferrari V, Hebert M, Sminchisescu C, Weiss Y, eds. Computer Vision – ECCV 2018. 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part X. Lecture Notes in Computer Science. Vol 11214. Cham: Springer International Publishing; 2018: 765-782.
Rhodin, H., Salzmann, M., & Fua, P. (2018). Unsupervised Geometry-Aware Representation for 3D Human Pose Estimation. In V. Ferrari, M. Hebert, C. Sminchisescu, & Y. Weiss (Eds.), Lecture Notes in Computer Science: Vol. 11214. Computer Vision – ECCV 2018. 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part X (pp. 765-782). Cham: Springer International Publishing. https://doi.org/10.1007/978-3-030-01249-6_46
Rhodin, Helge, Salzmann, Mathieu, and Fua, Pascal. 2018. “Unsupervised Geometry-Aware Representation for 3D Human Pose Estimation”. In Computer Vision – ECCV 2018. 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part X, ed. Vittorio Ferrari, Martial Hebert, Cristian Sminchisescu, and Yair Weiss, 11214:765-782. Lecture Notes in Computer Science. Cham: Springer International Publishing.
Rhodin, H., Salzmann, M., and Fua, P. (2018). “Unsupervised Geometry-Aware Representation for 3D Human Pose Estimation” in Computer Vision – ECCV 2018. 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part X, Ferrari, V., Hebert, M., Sminchisescu, C., and Weiss, Y. eds. Lecture Notes in Computer Science, vol. 11214, (Cham: Springer International Publishing), 765-782.
Rhodin, H., Salzmann, M., & Fua, P., 2018. Unsupervised Geometry-Aware Representation for 3D Human Pose Estimation. In V. Ferrari, et al., eds. Computer Vision – ECCV 2018. 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part X. Lecture Notes in Computer Science. no.11214 Cham: Springer International Publishing, pp. 765-782.
H. Rhodin, M. Salzmann, and P. Fua, “Unsupervised Geometry-Aware Representation for 3D Human Pose Estimation”, Computer Vision – ECCV 2018. 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part X, V. Ferrari, et al., eds., Lecture Notes in Computer Science, vol. 11214, Cham: Springer International Publishing, 2018, pp.765-782.
Rhodin, H., Salzmann, M., Fua, P.: Unsupervised Geometry-Aware Representation for 3D Human Pose Estimation. In: Ferrari, V., Hebert, M., Sminchisescu, C., and Weiss, Y. (eds.) Computer Vision – ECCV 2018. 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part X. Lecture Notes in Computer Science. 11214, p. 765-782. Springer International Publishing, Cham (2018).
Rhodin, Helge, Salzmann, Mathieu, and Fua, Pascal. “Unsupervised Geometry-Aware Representation for 3D Human Pose Estimation”. Computer Vision – ECCV 2018. 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part X. Ed. Vittorio Ferrari, Martial Hebert, Cristian Sminchisescu, and Yair Weiss. Cham: Springer International Publishing, 2018.Vol. 11214. Lecture Notes in Computer Science. 765-782.
Link(s) zu Volltext(en)
Access Level
Open Access