3-D pose estimation is an important direction for human pose estimation tasks. Aiming at the problems of restricted viewpoint and lack of depth information, this article proposes a two-stage representation refinement method for 3-D human pose estimation based on convex combination. It aims to solve the difficult problem of estimating 3-D human pose from 2-D image sequences, and can better utilize the relationship between each frame in the pose video sequence to produce more accurate results. Our work enables efficient 3-D pose estimation. This finding provides a boost to the direction of human pose estimation. Based on this, we have conducted sufficient experiments to prove that our method possesses better results and potential.

In the human pose estimation task, on the one hand, 3-D pose always has difficulty in dividing different 2-D poses if the view is limited; on the other hand, it is hard to reduce the lifting ambiguity because of the lack of depth information, it is an important and challenging problem. Therefore, two-stage representation refinement based on the convex combination for 3-D human pose estimation is proposed, in which the two-stage method includes a dense-spatial-temporal convolutional network and a local-to-refine network. The former is applied to determine the features between each video frame; the latter is used to get the different scales of pose details. It aims to address the difficulty of estimating 3-D human pose from 2-D image sequences. In such a way, it can better use the relations between every frame in the sequence of the pose video to produce more accurate results. Finally, we combine the above network with a block called convex combination to help refine the 3-D pose locatio...