论文标题
Interhand2.26m：从单个RGB图像中的3D交互手姿势估计的数据集和基线
InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Image
论文作者
论文摘要
分析手工互动是更好地理解人类行为的关键步骤。但是，3D手姿势估计中的大多数研究都集中在孤立的单手情况下。因此，我们首先提出（1）一个大规模数据集，Interhand 2.6m和（2）基线网络，Internet，用于从单个RGB图像中进行3D交互手动姿势估计。所提出的互惠2.6m由\ textbf {2.6m标记为单个和交互的手框}，并在来自多个受试者的各种姿势下组成。我们的互联网同时执行3D单打和交互的手姿势估计。在我们的实验中，当利用交互的手数据2.6m时，我们证明了3D相互作用的手姿势估计精度的巨大增长。我们还报告了Interhand 26M上Internet的准确性，这是该新数据集的强大基准。最后，我们显示了一般图像的3D相互作用姿势估计结果。我们的代码和数据集可在https://mks0601.github.io/interhand2.6m/上找到。
Analysis of hand-hand interactions is a crucial step towards better understanding human behavior. However, most researches in 3D hand pose estimation have focused on the isolated single hand case. Therefore, we firstly propose (1) a large-scale dataset, InterHand2.6M, and (2) a baseline network, InterNet, for 3D interacting hand pose estimation from a single RGB image. The proposed InterHand2.6M consists of \textbf{2.6M labeled single and interacting hand frames} under various poses from multiple subjects. Our InterNet simultaneously performs 3D single and interacting hand pose estimation. In our experiments, we demonstrate big gains in 3D interacting hand pose estimation accuracy when leveraging the interacting hand data in InterHand2.6M. We also report the accuracy of InterNet on InterHand2.6M, which serves as a strong baseline for this new dataset. Finally, we show 3D interacting hand pose estimation results from general images. Our code and dataset are available at https://mks0601.github.io/InterHand2.6M/.
