filename : Dib17c.pdf entry : inproceedings conference : Fifth International Conference on 3D Vision (3DV), Qingdao, China, October 10-12, 2017 pages : year : 2017 month : October title : How to Refine 3D Hand Pose Estimation from Unlabelled Depth Data ? subtitle : author : Endri Dibra and Thomas Wolf and Cengiz {\"{O}}ztireli and Markus Gross booktitle : Fifth International Conference on 3D Vision, 3DV 2017 ISSN/ISBN : editor : publisher : {IEEE} Computer Society publ.place : volume : issue : language : english keywords : 3D hand pose estimation, deep networks, unlabelled data, semi supervised learning, CNNs abstract : Data-driven approaches for hand pose estimation from depth images usually require a substantial amount of labelled training data which is quite hard to obtain. In this work, we show how a simple convolutional neural network, pre-trained only on synthetic depth images generated from a single 3D hand model, can be trained to adapt to unlabelled depth images from a real user’s hand. We validate our method on two existing and a new dataset that we capture, both quantitatively and qualitatively, demonstrating that we strongly compare to state-of-the-art methods. Additionally, this method can be seen as an extension to existing methods trained on limited datasets, which helps on boosting their performance on new ones.