“…Dex-Net 1.0 contains 13,252 3D mesh models: 8,987 from the SHREC 2014 challenge dataset [28], 2,539 from ModelNet40 [45], 1,371 from 3DNet [44], 129 from the KIT object database * [19], 120 from BigBIRD * [38], 80 from the Yale-CMU-Berkeley dataset * [8], and 26 from the Amazon Picking Challenge * scans ( * indicates laser-scanner data). We preprocess each mesh by removing unreferenced vertices, computing a reference frame with Principal Component Analysis (PCA) on the mesh vertices, setting the mesh center of mass z to the center of the mesh bounding box, and rescaling the synthetic meshes to fit the smallest dimension of the bounding box within w = 0.1m.…”