Recent years have witnessed significant progress in 3D hand mesh recovery. Nevertheless, because of the intrinsic 2D-to-3D ambiguity, recovering camera-space 3D information from a single RGB image remains challenging. To tackle this problem, we divide camera-space mesh recovery into two sub-tasks, i.e., root-relative mesh recovery and root recovery. First, joint landmarks and silhouette are extracted from a single input image to provide 2D cues for the 3D tasks. In the root-relative mesh recovery task, we exploit semantic relations among joints to generate a 3D mesh from the extracted 2D cues. Such generated 3D mesh coordinates are expressed relative to a root position, i.e., wrist of the hand. In the root recovery task, the root position is registered to the camera space by aligning the generated 3D mesh back to 2D cues, thereby completing camera-space 3D mesh recovery. Our pipeline is novel in that (1) it explicitly makes use of known semantic relations among joints and (2) it exploits 1D projections of the silhouette and mesh to achieve robust registration. Extensive experiments on popular datasets such as FreiHAND, RHD, and Human3.6M demonstrate that our approach achieves state-of-the-art performance on both root-relative mesh recovery and root recovery. Our code is publicly available at https://github.com/SeanChenxy/HandMesh.

中文翻译：

---

通过语义聚合和自适应2D-1D配准的相机空间手网格恢复

近年来，目睹了3D手工网格恢复的重大进步。然而，由于固有的2D到3D模糊性，从单个RGB图像恢复相机空间3D信息仍然具有挑战性。为了解决这个问题，我们将相机空间网格恢复分为两个子任务，即根相对网格恢复和根恢复。首先，从单个输入图像中提取联合地标和轮廓，以为3D任务提供2D提示。在根相对网格恢复任务中，我们利用关节之间的语义关系从提取的2D线索生成3D网格。相对于根部位置，即手的腕部，来表达这样生成的3D网格坐标。在根恢复任务中，通过将生成的3D网格对齐回2D线索，将根位置注册到相机空间，从而完成了相机空间3D网格恢复。我们的管道是新颖的，因为（1）明确利用关节之间的已知语义关系，并且（2）利用轮廓和网格的一维投影来实现鲁棒的配准。在常用数据集（例如FreiHAND，RHD和Human3.6M）上进行的大量实验表明，我们的方法在相对根网格恢复和根恢复方面均达到了最先进的性能。我们的代码可从https://github.com/SeanChenxy/HandMesh公开获得。6M证明了我们的方法在相对根网格恢复和根恢复方面都达到了最新的性能。我们的代码可从https://github.com/SeanChenxy/HandMesh公开获得。6M证明了我们的方法在相对根网格恢复和根恢复方面都达到了最新的性能。我们的代码可从https://github.com/SeanChenxy/HandMesh公开获得。