Rhodin, HelgeSalzmann, MathieuFua, Pascal2018-08-082018-08-082018-08-08201810.1007/978-3-030-01249-6_46https://infoscience.epfl.ch/handle/20.500.14299/147678Modern 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.3D reconstructionsemi-supervised trainingrepresentationlearningmonocular human pose reconstruction.text::conference output::conference proceedings::conference paper