论文标题
部分观察的全身意识
Full-Body Awareness from Partial Observations
论文作者
论文摘要
人类3D网格恢复和从消费者视频数据中学习世界的兴趣取得了长足进步。不幸的是，当前3D人网恢复的方法在消费者视频数据上的作用较差，因为在Internet上，相机的观点异常和侵略性截断是常态而不是稀有性。我们研究了这个问题，并为解决它做出了许多贡献：（i）我们提出了一个简单但高效的自我训练框架，该框架将人类3D网格恢复系统适应消费者视频，并将其应用于最近的两个系统； （ii）我们在四个消费者视频数据集中介绍了13K帧的评估协议和关键点注释，以研究此任务，包括对脱离图像关键的评估； （iii）我们表明，与基线相比，我们的方法显着改善了PCK和人类受试者的判断，这既可以训练它的数据集中的测试视频，以及在其他三个数据集中，没有进一步适应。项目网站：https：//crockwell.github.io/partial_humans
There has been great progress in human 3D mesh recovery and great interest in learning about the world from consumer video data. Unfortunately current methods for 3D human mesh recovery work rather poorly on consumer video data, since on the Internet, unusual camera viewpoints and aggressive truncations are the norm rather than a rarity. We study this problem and make a number of contributions to address it: (i) we propose a simple but highly effective self-training framework that adapts human 3D mesh recovery systems to consumer videos and demonstrate its application to two recent systems; (ii) we introduce evaluation protocols and keypoint annotations for 13K frames across four consumer video datasets for studying this task, including evaluations on out-of-image keypoints; and (iii) we show that our method substantially improves PCK and human-subject judgments compared to baselines, both on test videos from the dataset it was trained on, as well as on three other datasets without further adaptation. Project website: https://crockwell.github.io/partial_humans
