SupplementaryMaterial MultiviewHumanBodyReconstructionfrom UncalibratedCameras

It comes with ground truth 3D pose and follow its standard split for training and testing. MannequinChallenge is captured by a moving hand-held camera while subjects stay still in daily life scenarios. We reconstruct 3D body shape and pose using multiview images from those datasets and report MPJPE-PAmetricinTable1. We test run time for a different number of views within a frame. The graph convolutional mesh decoder has 7 layers, each with 256 channels.