DART: Articulated Hand Model with Diverse Accessories and Rich Textures
This work addresses the need for more realistic synthetic hand data in vision and graphics for digital twins, though it is incremental as it builds directly on MANO.
The paper tackles the limitation of existing hand morphable models like MANO by introducing DART, which adds diverse accessories and rich textures to synthesize photorealistic hand data, resulting in DARTset, a dataset of 800K high-fidelity synthetic images that improves generalization in hand pose estimation and mesh recovery tasks.
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