论文标题
Handoccnet：闭塞3D手网估计网络
HandOccNet: Occlusion-Robust 3D Hand Mesh Estimation Network
论文作者
论文摘要
双手通常会被物体严重遮住，这使得3D手网估计具有挑战性。以前的作品通常在封闭的地区忽略了信息。但是，我们认为被阻塞的区域与双手有很强的相关性，因此它们可以提供非常有益的信息以获得完整的3D手网格估计。因此，在这项工作中，我们提出了一种新颖的3D手网网估计网络杂种，可以将信息完全利用在被遮挡的区域中，作为增强图像特征并使其更丰富的次要手段。为此，我们设计了两个连续的基于变压器的模块，称为功能注入变压器（fit）和自我增强变压器（SET）。通过考虑它们的相关性，将注入信息的注射信息纳入遮挡区域。集合通过使用自发机制来完善拟合的输出。通过将手信息注入封闭区域，我们的杂种可以在3D手网格基准测试中达到最先进的性能，其中包含具有挑战性的手动闭塞。这些代码可在：https：//github.com/namepllet/handoccnet中获得。
Hands are often severely occluded by objects, which makes 3D hand mesh estimation challenging. Previous works often have disregarded information at occluded regions. However, we argue that occluded regions have strong correlations with hands so that they can provide highly beneficial information for complete 3D hand mesh estimation. Thus, in this work, we propose a novel 3D hand mesh estimation network HandOccNet, that can fully exploits the information at occluded regions as a secondary means to enhance image features and make it much richer. To this end, we design two successive Transformer-based modules, called feature injecting transformer (FIT) and self- enhancing transformer (SET). FIT injects hand information into occluded region by considering their correlation. SET refines the output of FIT by using a self-attention mechanism. By injecting the hand information to the occluded region, our HandOccNet reaches the state-of-the-art performance on 3D hand mesh benchmarks that contain challenging hand-object occlusions. The codes are available in: https://github.com/namepllet/HandOccNet.
