arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1804.03390cs.CVcs.LG
收藏

通过预测不同的视图来学习特定的姿势表示

Learning Pose Specific Representations by Predicting Different Views

Institute for Computer Graphics and Vision(计算机图形与视觉研究所);Graz University of Technology(格拉茨理工大学)

Georg Poier, David Schinagl, Horst Bischof

摘要:

学习关节式物体的姿态估计所需的标记数据难以以期望的数量、真实性、密度和准确性提供。为了解决这个问题,我们开发了一种方法来学习表示,这是非常具体的关节姿势,而不需要标记的训练数据。我们利用的观察,一个已知的对象的对象姿态是预测的外观在任何已知的视图。也就是说,仅给定手的姿势和形状参数,可以近似从任何视点的手的外观。为了利用这一观察结果,我们训练了一个模型,该模型在给定来自一个视图的输入的情况下,估计一个潜在的表示,该表示经过训练,可以预测从另一个视点捕获的对象的外观。因此,唯一必要的监督是第二种观点。该模型的训练过程揭示了潜在空间中隐含的姿势表示。重要的是,在测试时,可以仅使用单个视图来推断姿势表示。在定性和定量的实验中,我们表明,学习表示捕捉详细的姿态信息。此外,当使用标记和未标记数据联合训练所提出的方法时,它始终超过其完全监督的对应方法的性能,同时将所需的标记样本的数量减少至少一个数量级。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑