No abstract

Figure 1: GanHand predicts hand shape and pose for grasping multiple objects given a single RGB image. The figure shows sample results on the YCB-Affordance dataset we propose, the largest dataset of human grasp affordances in real scenes.

The problem of predicting human motion given a sequence of past observations is at the core of many applications in robotics and computer vision. Current state-ofthe-art formulate this problem as a sequence-to-sequence task, in which a historical of 3D skeletons feeds a Recurrent Neural Network (RNN) that predicts future movements, typically in the order of 1 to 2 seconds. However, one aspect that has been obviated so far, is the fact that human motion is inherently driven by interactions with objects and/or other humans in the environment. In this paper, we explore this scenario using a novel context-aware motion prediction architecture. We use a semantic-graph model where the nodes parameterize the human and objects in the scene and the edges their mutual interactions. These interactions are iteratively learned through a graph attention layer, fed with the past observations, which now include both object and human body motions. Once this semantic graph is learned, we inject it to a standard RNN to predict future movements of the human/s and object/s. We consider two variants of our architecture, either freezing the contextual interactions in the future of updating them. A thorough evaluation in the "Whole-Body Human Motion Database" [29] shows that in both cases, our context-aware networks clearly outperform baselines in which the context information is not considered.

♠❛❦❡s ✐t ✈❡r② ❞✐✣❝✉•t t♦ ✐❞❡♥t✐❢② t❤❡ t②♣❡ ♦❢ ❣❛r♠❡♥t ❛♥❞ •♦❝❛t❡ t❤❡ ♠♦st r❡•❡✈❛♥t ♣❛rts t❤❛t

Figure 1: We introduce SMPLicit, a fully differentiable generative model for clothed bodies, capable of representing garments with different topology. The four figures on the left show the application of the model to the problem of 3D body and cloth reconstruction from an input image. We are able to predict different models per cloth, even for multi-layer cases. Three right-most images: The model can also be used for editing the outfits, removing/adding new garments and re-posing the body.