Towards Viewpoint Invariant 3D Human Pose Estimation

Code

• github.com/zhengkang86/ram_person_id
  torch★ 0
• github.com/mks0601/V2V-PoseNet_RELEASE
  pytorch★ 0

Abstract

We propose a viewpoint invariant model for 3D human pose estimation from a single depth image. To achieve this, our discriminative model embeds local regions into a learned viewpoint invariant feature space. Formulated as a multi-task learning problem, our model is able to selectively predict partial poses in the presence of noise and occlusion. Our approach leverages a convolutional and recurrent network architecture with a top-down error feedback mechanism to self-correct previous pose estimates in an end-to-end manner. We evaluate our model on a previously published depth dataset and a newly collected human pose dataset containing 100K annotated depth images from extreme viewpoints. Experiments show that our model achieves competitive performance on frontal views while achieving state-of-the-art performance on alternate viewpoints.

Tasks

Benchmark Results

Reproductions