We present a convolutional autoencoder that enables high fidelity volumetric reconstructions of human performance to be captured from multi-view video comprising only a small set of camera views. Our method yields similar end-to-end reconstruction error to that of a probabilistic visual hull computed using significantly more (double or more) viewpoints. We use a deep prior implicitly learned by the autoencoder trained over a dataset of view-ablated multi-view video footage of a wide range of subjects and actions. This opens up the possibility of high-end volumetric performance capture in on-set and prosumer scenarios where time or cost prohibit a high witness camera count.


        AUTHOR = "Gilbert, Andrew and Volino, Marco and Collomosse, John and Hilton, Adrian ",
        TITLE = "Volumetric performance capture from minimal camera viewpoints",
    	BOOKTITLE = " European Conference on Computer Vision (ECCV'18)",
        YEAR = "2018",


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