Toward Reliable Human Pose Forecasting with Uncertainty
arXiv:2304.06707 · doi:10.1109/LRA.2024.3374188
Abstract
Recently, there has been an arms race of pose forecasting methods aimed at solving the spatio-temporal task of predicting a sequence of future 3D poses of a person given a sequence of past observed ones. However, the lack of unified benchmarks and limited uncertainty analysis have hindered progress in the field. To address this, we first develop an open-source library for human pose forecasting, including multiple models, supporting several datasets, and employing standardized evaluation metrics, with the aim of promoting research and moving toward a unified and consistent evaluation. Second, we devise two types of uncertainty in the problem to increase performance and convey better trust: 1) we propose a method for modeling aleatoric uncertainty by using uncertainty priors to inject knowledge about the pattern of uncertainty. This focuses the capacity of the model in the direction of more meaningful supervision while reducing the number of learned parameters and improving stability; 2) we introduce a novel approach for quantifying the epistemic uncertainty of any model through clustering and measuring the entropy of its assignments. Our experiments demonstrate up to improvements in forecasting at short horizons, with no loss on longer horizons on Human3.6M, AMSS, and 3DPW datasets, and better performance in uncertainty estimation. The code is available online at https://github.com/vita-epfl/UnPOSed.
Published in RA-L 2024
References in corpus (6)
- Uncertainty Estimation Using a Single Deep Deterministic Neural Network
- Action Anticipation: Reading the Intentions of Humans and Robots
- Diverse Human Motion Prediction Guided by Multi-Level Spatial-Temporal Anchors
- Pedestrian 3D Bounding Box Prediction
- Sim-to-Real Causal Transfer: A Metric Learning Approach to Causally-Aware Interaction Representations
- Social-Transmotion: Promptable Human Trajectory Prediction