论文标题
纳帕：神经艺术人姿势放大器
NAPA: Neural Art Human Pose Amplifier
论文作者
论文摘要
这是CSCI-GA.2271-001的项目报告。我们针对艺术图像中的人类姿势估计。对于这个目标，我们设计了一个使用神经样式转移进行姿势回归的端到端系统。我们为任意风格的转移收集了277风格的套件，并建立了艺术281图像测试集。我们直接在测试集上运行姿势回归，并显示出令人鼓舞的结果。对于姿势回归，我们提出了一个2D诱导的骨图，从中提取了姿势。为了帮助这样的提升，我们还注释了完整的野外MPII数据集的伪3D标签。此外，我们将另一种样式转移作为自我监督以提高2D。我们进行广泛的消融研究来分析引入的特征。我们还将端到端的每种培训与端到端进行比较，并暗示了风格转移和姿势回归之间的权衡。最后，我们将模型概括为现实世界的人类数据集，并显示其作为通用姿势模型的潜力。我们在附录中解释了理论基础。我们在https://github.com/strawberryfg/napa-nst-hpe，数据和视频上发布代码。
This is the project report for CSCI-GA.2271-001. We target human pose estimation in artistic images. For this goal, we design an end-to-end system that uses neural style transfer for pose regression. We collect a 277-style set for arbitrary style transfer and build an artistic 281-image test set. We directly run pose regression on the test set and show promising results. For pose regression, we propose a 2d-induced bone map from which pose is lifted. To help such a lifting, we additionally annotate the pseudo 3d labels of the full in-the-wild MPII dataset. Further, we append another style transfer as self supervision to improve 2d. We perform extensive ablation studies to analyze the introduced features. We also compare end-to-end with per-style training and allude to the tradeoff between style transfer and pose regression. Lastly, we generalize our model to the real-world human dataset and show its potentiality as a generic pose model. We explain the theoretical foundation in Appendix. We release code at https://github.com/strawberryfg/NAPA-NST-HPE, data, and video.
