Optimizing MPJPE promotes miscalibration in multi-hypothesis human pose lifting
Paweł Pierzchlewicz
2023 Virtual oral
in
Affinity Event: Tiny Papers Showcase Day (a DEI initiative)
in
Affinity Event: Tiny Papers Showcase Day (a DEI initiative)
Abstract
Due to depth ambiguities and occlusions, lifting 2D poses to 3D is a highly ill-posed problem. Well-calibrated distributions of possible poses can make these ambiguities explicit and preserve the resulting uncertainty for downstream tasks, thus providing the necessary trustworthiness in safety-critical domains. This study shows that multiple hypothesis pose estimation methods produce miscalibrated distributions. We identify that miscalibration can be attributed to the optimization of mean per joint position error MPJPE. In a series of simulations, we show th
Video
Chat is not available.
Successful Page Load