AdaptivePose: Human Parts as Adaptive Points

TL;DR

AdaptivePose introduces a novel single-stage multi-person pose estimation method that uses an adaptive point set to represent human parts, significantly improving efficiency and accuracy over traditional two-stage approaches.

Contribution

The paper proposes a new body representation using adaptive points, enabling a more precise and efficient single-stage pose estimation network called AdaptivePose.

Findings

Achieves 67.4% AP at 29.4 fps with DLA-34 on COCO.

Achieves 71.3% AP at 9.1 fps with HRNet-W48 on COCO.

Outperforms existing methods in speed-accuracy trade-offs.

Abstract

Multi-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.