ArtiBoost：通过在线探索和合成来增强关节式3D手部对象姿态估计
ArtiBoost: Boosting Articulated 3D Hand-Object Pose Estimation via Online Exploration and Synthesis
摘要：
从单个RGB图像估计关节式3D手部对象姿势是一个高度模糊且具有挑战性的问题，需要包含不同手部姿势、对象类型和相机视点的大规模数据集。大多数真实世界的数据集缺乏这些数据。相比之下，数据合成可以很容易地分别确保这些差异。然而，构建有效和多样的手-物体交互以及从大量的合成数据中有效地学习仍然是具有挑战性的。为了解决上述问题，我们提出了ArtiBoost，一个轻量级的在线数据增强方法。ArtiBoost通过在复合手对象配置和视点空间（CCV-space）中采样，可以覆盖不同的手对象姿态和摄像机视点，并通过损失反馈和样本重新加权，自适应地丰富当前难以识别的项。ArtiBoost在学习管道内交替执行数据探索和合成，这些合成数据被混合到真实世界的源数据中进行训练。我们在简单的学习基线网络上应用ArtiBoost，并在几个手部对象基准测试中见证了性能的提升。我们的模型和代码可以在https://github.com/lixiny/ArtiBoost上找到。
英文摘要：
Estimating the articulated 3D hand-object pose from a single RGB image is a highly ambiguous and challenging problem, requiring large-scale datasets that contain diverse hand poses, object types, and camera viewpoints. Most real-world datasets lack these diversities. In contrast, data synthesis can easily ensure those diversities separately. However, constructing both valid and diverse hand-object interactions and efficiently learning from the vast synthetic data is still challenging. To address the above issues, we propose ArtiBoost, a lightweight online data enhancement method. ArtiBoost can cover diverse hand-object poses and camera viewpoints through sampling in a Composited hand-object Configuration and Viewpoint space (CCV-space) and can adaptively enrich the current hard-discernable items by loss-feedback and sample re-weighting. ArtiBoost alternatively performs data exploration and synthesis within a learning pipeline, and those synthetic data are blended into real-world source data for training. We apply ArtiBoost on a simple learning baseline network and witness the performance boost on several hand-object benchmarks. Our models and code are available at https://github.com/lixiny/ArtiBoost.
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。
