PALM: A Dataset and Baseline for Learning Multi-subject Hand Prior

TL;DR

PALM introduces a large-scale, diverse dataset of high-quality hand scans and images, along with a baseline model for realistic, relightable hand avatar creation from single images, advancing hand modeling research.

Contribution

The paper provides a comprehensive dataset of 13k hand scans and 90k multi-view images, and proposes PALM-Net, a baseline for multi-subject hand prior learning using physically based inverse rendering.

Findings

PALM dataset covers diverse skin tones, ages, and geometries.

PALM-Net enables realistic, relightable hand avatar generation from single images.

The dataset and model improve hand modeling accuracy and personalization.

Abstract

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.