arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2308.03411cs.CV
收藏

无标签之马:基于未标注图像与合成先验的自监督马匹姿态估计

A Horse with no Labels: Self-Supervised Horse Pose Estimation from Unlabelled Images and Synthetic Prior

University of Leeds(利兹大学)

Jose Sosa, David Hogg

AI总结:

本文提出一种仅需未标注图像和少量合成2D姿态先验的自监督方法,无需任何真实姿态标注即可同时学习马匹的准确3D和2D姿态,并验证了极低假设条件下动物姿态估计的可行性。

摘要:

获取用于训练动物姿态估计深度学习方法的标注数据具有挑战性。近年来,合成数据被广泛用于姿态估计任务,但大多数方法仍依赖利用合成图像和标签的有监督学习范式。训练能否完全无监督?极小的合成数据集是否足够?对于估计动物姿态,我们能够做出的最小假设是什么?我们的方案通过一种简单而有效的自监督方法来回答这些问题,该方法仅假设可获取未标注图像和一小组合成2D姿态。我们完全消除了对任何3D或2D姿态标注(或复杂3D动物模型)的需求,而令人惊讶的是,我们的方法仍能同时学习准确的3D和2D姿态。我们使用主要从YouTube视频中收集的未标注马匹图像以及由2D合成姿态构成的先验来训练我们的方法。后者的规模比训练所需图像数量小三倍。我们在一个具有挑战性的马匹图像集上测试了我们的方法,并评估了预测的3D和2D姿态。我们证明,即使仅以未标注图像和由合成数据生成的一小组2D姿态作为最小假设,也有可能学习到准确的动物姿态。鉴于最低要求以及未标注数据的丰富性,我们的方法可以轻松部署到不同的动物上。

英文摘要:

Obtaining labelled data to train deep learning methods for estimating animal pose is challenging. Recently, synthetic data has been widely used for pose estimation tasks, but most methods still rely on supervised learning paradigms utilising synthetic images and labels. Can training be fully unsupervised? Is a tiny synthetic dataset sufficient? What are the minimum assumptions that we could make for estimating animal pose? Our proposal addresses these questions through a simple yet effective self-supervised method that only assumes the availability of unlabelled images and a small set of synthetic 2D poses. We completely remove the need for any 3D or 2D pose annotations (or complex 3D animal models), and surprisingly our approach can still learn accurate 3D and 2D poses simultaneously. We train our method with unlabelled images of horses mainly collected for YouTube videos and a prior consisting of 2D synthetic poses. The latter is three times smaller than the number of images needed for training. We test our method on a challenging set of horse images and evaluate the predicted 3D and 2D poses. We demonstrate that it is possible to learn accurate animal poses even with as few assumptions as unlabelled images and a small set of 2D poses generated from synthetic data. Given the minimum requirements and the abundance of unlabelled data, our method could be easily deployed to different animals.

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。

↑