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

Harry Zhang, Luca Carlone
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:74583-74601, 2025.

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. Interactive 3D visualization, code, and data will be available at https://sites.google.com/view/champpp.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-zhang25g, title = {{CUPS}: Improving Human Pose-Shape Estimators with Conformalized Deep Uncertainty}, author = {Zhang, Harry and Carlone, Luca}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {74583--74601}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/zhang25g/zhang25g.pdf}, url = {https://proceedings.mlr.press/v267/zhang25g.html}, 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. Interactive 3D visualization, code, and data will be available at https://sites.google.com/view/champpp.} }
Endnote
%0 Conference Paper %T CUPS: Improving Human Pose-Shape Estimators with Conformalized Deep Uncertainty %A Harry Zhang %A Luca Carlone %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-zhang25g %I PMLR %P 74583--74601 %U https://proceedings.mlr.press/v267/zhang25g.html %V 267 %X 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. Interactive 3D visualization, code, and data will be available at https://sites.google.com/view/champpp.
APA
Zhang, H. & Carlone, L.. (2025). CUPS: Improving Human Pose-Shape Estimators with Conformalized Deep Uncertainty. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:74583-74601 Available from https://proceedings.mlr.press/v267/zhang25g.html.

Related Material