Learning Pose Specific Representations by Predicting Different Views
| Autor: | David Schinagl, Horst Bischof, Georg Poier |
|---|---|
| Předmět: |
FOS: Computer and information sciences
Computer science Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition 02 engineering and technology 010501 environmental sciences Space (commercial competition) 01 natural sciences Data modeling Machine Learning (cs.LG) 0202 electrical engineering electronic engineering information engineering Pose 0105 earth and related environmental sciences I.2.10 business.industry I.2.6 I.4.5 I.5.4 Representation (systemics) Process (computing) Pattern recognition Object (computer science) I.4.10 Computer Science - Learning Task analysis I.4.8 020201 artificial intelligence & image processing Artificial intelligence business |
| Zdroj: | TU Graz CVPR |
| Popis: | 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. Comment: CVPR 2018 (Spotlight); Project Page at https://poier.github.io/PreView/ |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|