论文标题
DART：具有不同配件和丰富纹理的铰接式手模型
DART: Articulated Hand Model with Diverse Accessories and Rich Textures
论文作者
论文摘要
人类生产力和智力的承载者手因最近的数字双胞胎发烧而引起了很多关注。在不同的手形模型中，Mano已被广泛用于视觉和图形社区。但是，Mano无视纹理和配件，这在很大程度上限制了其综合逼真的手数据的功能。在本文中，我们扩展了Mano具有不同配件和丰富纹理的Mano，即Dart。 DART由50个每日3D配件组成，外观和形状各不相同，325个手工制作的2D纹理地图涵盖了不同种类的瑕疵或化妆品。还提供了Unity GUI，以生成具有用户定义的设置，例如姿势，相机，背景，照明，纹理和配件的合成手数据。最后，我们释放了包含大规模（800k）的高保真合成手图像的Dartset，并与完美的3D标签配对。实验证明了其在多样性方面的优势。作为对现有手数据集的补充，Dartset在手动姿势估计和网格恢复任务中都提高了概括。 RAW成分（纹理，配件），Unity GUI，源代码和DARTSET可在dart2022.github.io上公开获得
Hand, the bearer of human productivity and intelligence, is receiving much attention due to the recent fever of digital twins. Among different hand morphable models, MANO has been widely used in vision and graphics community. However, MANO disregards textures and accessories, which largely limits its power to synthesize photorealistic hand data. In this paper, we extend MANO with Diverse Accessories and Rich Textures, namely DART. DART is composed of 50 daily 3D accessories which varies in appearance and shape, and 325 hand-crafted 2D texture maps covers different kinds of blemishes or make-ups. Unity GUI is also provided to generate synthetic hand data with user-defined settings, e.g., pose, camera, background, lighting, textures, and accessories. Finally, we release DARTset, which contains large-scale (800K), high-fidelity synthetic hand images, paired with perfect-aligned 3D labels. Experiments demonstrate its superiority in diversity. As a complement to existing hand datasets, DARTset boosts the generalization in both hand pose estimation and mesh recovery tasks. Raw ingredients (textures, accessories), Unity GUI, source code and DARTset are publicly available at dart2022.github.io
