CUPS: Improving Human Pose-Shape Estimators with Conformalized Deep Uncertainty

TL;DR

CUPS is a novel approach that combines deep uncertainty modeling with conformal prediction to improve 3D human pose and shape estimation from RGB videos, providing calibrated uncertainty estimates and state-of-the-art results.

Contribution

The paper introduces a new method integrating uncertainty quantification into 3D human pose-shape estimation using conformal prediction, with theoretical bounds for coverage gaps.

Findings

Achieves state-of-the-art performance on multiple datasets.

Provides calibrated uncertainty estimates for predictions.

Develops theoretical bounds for conformal prediction coverage gaps.

Abstract

We introduce CUPS, a novel method for learning sequence-to-sequence 3D human shapes and poses from RGB videos with uncertainty quantification. To improve on top of prior work, we develop a method to generate and score multiple hypotheses during training, effectively integrating uncertainty quantification into the learning process. This process results in a deep uncertainty function that is trained end-to-end with the 3D pose estimator. Post-training, the learned deep uncertainty model is used as the conformity score, which can be used to calibrate a conformal predictor in order to assess the quality of the output prediction. Since the data in human pose-shape learning is not fully exchangeable, we also present two practical bounds for the coverage gap in conformal prediction, developing theoretical backing for the uncertainty bound of our model. Our results indicate that by taking advantage of deep uncertainty with conformal prediction, our method achieves state-of-the-art performance across various metrics and datasets while inheriting the probabilistic guarantees of conformal prediction.