Deep Cap: Monocular Human Performance Capture Using Weak Supervision ( CVPR 2020) Oral

Human performance capture is a highly important computer vision problem with many applications in movie production and virtual, augmented reality. Many previous performance capture approaches either required expensive multiview setups or did not recover dense spacetime coherent geometry with frametoframe correspondences. We propose a novel deep learning approach for monocular dense human performance capture. Our method is trained in a weakly supervised manner based on multiview supervision completely re