PALM: A Dataset and Baseline for Learning Multi-subject Hand Prior
This addresses the problem of limited datasets for hand modeling in computer vision and graphics, providing a valuable resource for researchers, though it is incremental in building upon existing hand avatar methods.
The authors tackled the challenge of creating personalized hand avatars from images by introducing PALM, a large-scale dataset with 13k hand scans from 263 subjects and 90k multi-view images, and PALM-Net, a baseline model that enables realistic, relightable single-image hand avatar personalization.
The ability to grasp objects, signal with gestures, and share emotion through touch all stem from the unique capabilities of human hands. Yet creating high-quality personalized hand avatars from images remains challenging due to complex geometry, appearance, and articulation, particularly under unconstrained lighting and limited views. Progress has also been limited by the lack of datasets that jointly provide accurate 3D geometry, high-resolution multiview imagery, and a diverse population of subjects. To address this, we present PALM, a large-scale dataset comprising 13k high-quality hand scans from 263 subjects and 90k multi-view images, capturing rich variation in skin tone, age, and geometry. To show its utility, we present a baseline PALM-Net, a multi-subject prior over hand geometry and material properties learned via physically based inverse rendering, enabling realistic, relightable single-image hand avatar personalization. PALM's scale and diversity make it a valuable real-world resource for hand modeling and related research.