First full body human-object interaction dataset with multi-view RGBD frames and corresponding 3D SMPL and object fits along with the annotated contacts between them.
An approach to synthesize highly photorealistic synthetic images of 3D object models, which is used to train a convolutional neural network for detecting the objects in real images.
A dataset of 100k synthetic faces with 2D landmark and per-pixel segmentation labels from a procedurally-generated parametric 3D face model with a comprehensive library of hand-crafted assets
