Abstract
We propose a new bottom-up method for multiperson 2D human pose estimation that is particularly
well suited for urban mobility such as self-driving cars
and delivery robots. The new method, PifPaf, uses a
Part Intensity Field (PIF) to localize body parts and a
Part Association Field (PAF) to associate body parts
with each other to form full human poses. Our method
outperforms previous methods at low resolution and in
crowded, cluttered and occluded scenes thanks to (i) our
new composite field PAF encoding fine-grained information and (ii) the choice of Laplace loss for regressions which incorporates a notion of uncertainty. Our
architecture is based on a fully convolutional, singleshot, box-free design. We perform on par with the existing state-of-the-art bottom-up method on the standard COCO keypoint task and produce state-of-the-art
results on a modified COCO keypoint task for the transportation domain.