Abstract

We present a method for simultaneously estimating 3D human pose and body shape from a sparse set of wide-baseline camera views. We train a symmetric convolutional autoencoder with a dual loss that enforces learning of a latent representation that encodes skeletal joint positions, and at the same time learns a deep representation of volumetric body shape. We harness the latter to up-scale input volumetric data by a factor of 4 times, whilst recovering a 3D estimate of joint positions with equal or greater accuracy than the state of the art. Inference runs in real-time (25 fps) and has the potential for passive human behaviour monitoring where there is a requirement for high fidelity estimation of human body shape and pose.




Citation

    @inproceedings{trumble:eccv:2018,
        AUTHOR = "Trumble, Matthew and Gilbert, Andrew and Hilton, Adrian and Collomosse, John ",
        TITLE = "Deep Autoencoder for Combined Human Pose Estimation and Body Model Upscaling",
    	BOOKTITLE = "European Conference on Computer Vision (ECCV'18)",
        YEAR = "2018",
    }
	    

Acknowledgments

This work was supported by the InnovateUK TotalCapture project grant agreement 102685.