Abstract: We propose the task of forecasting characteristic 3D poses: from a monocular video observation of a person, to predict a future 3D pose of that person in a likely action-defining, characteristic pose - for instance, from observing a person reaching for a banana, predict the pose of the person eating the banana. Prior work on human motion prediction estimates future poses at fixed time intervals. Although easy to define, this frame-by-frame formulation confounds temporal and intentional aspects of human action. Instead, we define a semantically meaningful pose prediction task that decouples the predicted pose from time, taking inspiration from goal-directed behavior. To predict characteristic poses, we propose a probabilistic approach that first models the possible multi-modality in the distribution of likely characteristic poses. It then samples future pose hypotheses from the predicted distribution in an autoregressive fashion to model dependencies between joints and finally optimizes the resulting pose with bone length and angle constraints. To evaluate our method, we construct a dataset of manually annotated characteristic 3D poses. Our experiments with this dataset suggest that our proposed probabilistic approach outperforms state-of-the-art methods by 22% on average.
Authors: Christian Diller, Thomas Funkhouser, Angela Dai (Technical University of Munich, Google)