Learning Pose Specific Representations by Predicting Different Views

TL;DR

This paper introduces a method to learn detailed pose-specific representations of articulated objects using view prediction, reducing the need for labeled data and improving pose estimation accuracy.

Contribution

The proposed approach learns pose representations without labeled data by predicting views, outperforming fully supervised methods with significantly less labeled data.

Findings

Learned representations capture detailed pose information

Outperforms fully supervised methods with less labeled data

Reduces labeled data requirement by at least tenfold

Abstract

The labeled data required to learn pose estimation for articulated objects is difficult to provide in the desired quantity, realism, density, and accuracy. To address this issue, we develop a method to learn representations, which are very specific for articulated poses, without the need for labeled training data. We exploit the observation that the object pose of a known object is predictive for the appearance in any known view. That is, given only the pose and shape parameters of a hand, the hand's appearance from any viewpoint can be approximated. To exploit this observation, we train a model that -- given input from one view -- estimates a latent representation, which is trained to be predictive for the appearance of the object when captured from another viewpoint. Thus, the only necessary supervision is the second view. The training process of this model reveals an implicit pose representation in the latent space. Importantly, at test time the pose representation can be inferred using only a single view. In qualitative and quantitative experiments we show that the learned representations capture detailed pose information. Moreover, when training the proposed method jointly with labeled and unlabeled data, it consistently surpasses the performance of its fully supervised counterpart, while reducing the amount of needed labeled samples by at least one order of magnitude.