AdaptivePose: Human Parts as Adaptive Points
This addresses the problem of high computation cost and low efficiency in multi-person pose estimation for computer vision applications, offering a more compact and efficient pipeline.
The paper tackles the inefficiency of two-stage multi-person pose estimation by proposing AdaptivePose, a single-stage method that represents human parts as adaptive points, achieving 67.4% AP at 29.4 fps and 71.3% AP at 9.1 fps on COCO test-dev.
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.