AdaptivePose: Human Parts as Adaptive Points
Keywords:Computer Vision (CV)
AbstractMulti-person pose estimation methods generally follow top-down and bottom-up paradigms, both of which can be considered as two-stage approaches thus leading to the high computation cost and low efficiency. Towards a compact and efficient pipeline for multi-person pose estimation task, in this paper, we propose to represent the human parts as points and present a novel body representation, which leverages an adaptive point set including the human center and seven human-part related points to represent the human instance in a more fine-grained manner. The novel representation is more capable of capturing the various pose deformation and adaptively factorizes the long-range center-to-joint displacement thus delivers a single-stage differentiable network to more precisely regress multi-person pose, termed as AdaptivePose. For inference, our proposed network eliminates the grouping as well as refinements and only needs a single-step disentangling process to form multi-person pose. Without any bells and whistles, we achieve the best speed-accuracy trade-offs of 67.4% AP / 29.4 fps with DLA-34 and 71.3% AP / 9.1 fps with HRNet-W48 on COCO test-dev dataset.
How to Cite
Xiao, Y., Wang, X. J., Yu, D., Wang, G., Zhang, Q., & HE, M. (2022). AdaptivePose: Human Parts as Adaptive Points. Proceedings of the AAAI Conference on Artificial Intelligence, 36(3), 2813-2821. https://doi.org/10.1609/aaai.v36i3.20185
AAAI Technical Track on Computer Vision III