Convolutional Pose Machines

Code

• github.com/CMU-Perceptual-Computing-Lab/convolutional-pose-machines-release
  OfficialIn papernone★ 0
• github.com/open-mmlab/mmpose
  pytorch★ 7,439
• github.com/yinzhiyan43/openpose-dev
  pytorch★ 0
• github.com/digital-thinking/deep-posemachine
  tf★ 0
• github.com/ostadabbas/in-bed-pose-estimation
  none★ 0
• github.com/chanyn/3Dpose_ssl
  tf★ 0
• github.com/techforgood-kiran/ai
  pytorch★ 0
• github.com/zyxcambridge/openpose_all
  pytorch★ 0
• github.com/laobaiswag/openpose1
  pytorch★ 0
• github.com/namedBen/Convolutional-Pose-Machines-Pytorch
  pytorch★ 0

Abstract

Pose Machines provide a sequential prediction framework for learning rich implicit spatial models. In this work we show a systematic design for how convolutional networks can be incorporated into the pose machine framework for learning image features and image-dependent spatial models for the task of pose estimation. The contribution of this paper is to implicitly model long-range dependencies between variables in structured prediction tasks such as articulated pose estimation. We achieve this by designing a sequential architecture composed of convolutional networks that directly operate on belief maps from previous stages, producing increasingly refined estimates for part locations, without the need for explicit graphical model-style inference. Our approach addresses the characteristic difficulty of vanishing gradients during training by providing a natural learning objective function that enforces intermediate supervision, thereby replenishing back-propagated gradients and conditioning the learning procedure. We demonstrate state-of-the-art performance and outperform competing methods on standard benchmarks including the MPII, LSP, and FLIC datasets.

Tasks

Benchmark Results

Reproductions