“Unsupervised Incremental Learning for Hand Shape and Pose Estimation” by Kalshetti and Chaudhuri

  • ©Pratik Kalshetti and Parag Chaudhuri

  • ©Pratik Kalshetti and Parag Chaudhuri


Entry Number: 96


    Unsupervised Incremental Learning for Hand Shape and Pose Estimation



    We present an unsupervised incremental learning method for refining hand shape and pose estimation. We propose a refiner network (RefNet) that can augment a state-of-the-art hand tracking system (BaseNet) by refining its estimations on unlabeled data. At each input depth frame, the estimations from the BaseNet are iteratively refined by RefNet using a model-fitting strategy. During this process, the RefNet adapts to the input data characteristics by incremental learning. We show that our method provides more accurate hand shape and pose estimates on both a standard dataset and real data.


    • Markus Oberweger, Paul Wohlhart, and Vincent Lepetit. 2015. Training a feedback loop for hand pose estimation. In Proc. IEEE CVPR. 3316–3324. 
    • Konstantin Shmelkov, Cordelia Schmid, and Karteek Alahari. 2017. Incremental learning of object detectors without catastrophic forgetting. In Proc. IEEE CVPR. 3400– 3409. 
    • Jonathan Taylor, Lucas Bordeaux, Thomas Cashman, Bob Corish, Cem Keskin, Toby Sharp, Eduardo Soto, David Sweeney, Julien Valentin, Benjamin Luff, et al. 2016. Efficient and precise interactive hand tracking through joint, continuous optimization of pose and correspondences. ACM ToG 35, 4 (2016), 143. 
    • Anastasia Tkach, Andrea Tagliasacchi, Edoardo Remelli, Mark Pauly, and Andrew Fitzgibbon. 2017. Online generative model personalization for hand tracking. ACM ToG 36, 6 (2017), 243. 
    • Jonathan Tompson, Murphy Stein, Yann Lecun, and Ken Perlin. 2014. Real-time continuous pose recovery of human hands using convolutional networks. ACM ToG 33 (August 2014), 169:1–169:10.