DeepAI AI Chat
Log In Sign Up

A Skeleton-Driven Neural Occupancy Representation for Articulated Hands

by   Korrawe Karunratanakul, et al.
ETH Zurich

We present Hand ArticuLated Occupancy (HALO), a novel representation of articulated hands that bridges the advantages of 3D keypoints and neural implicit surfaces and can be used in end-to-end trainable architectures. Unlike existing statistical parametric hand models (e.g. MANO), HALO directly leverages 3D joint skeleton as input and produces a neural occupancy volume representing the posed hand surface. The key benefits of HALO are (1) it is driven by 3D key points, which have benefits in terms of accuracy and are easier to learn for neural networks than the latent hand-model parameters; (2) it provides a differentiable volumetric occupancy representation of the posed hand; (3) it can be trained end-to-end, allowing the formulation of losses on the hand surface that benefit the learning of 3D keypoints. We demonstrate the applicability of HALO to the task of conditional generation of hands that grasp 3D objects. The differentiable nature of HALO is shown to improve the quality of the synthesized hands both in terms of physical plausibility and user preference.


page 1

page 14

page 16

page 21

page 22


Coupling Explicit and Implicit Surface Representations for Generative 3D Modeling

We propose a novel neural architecture for representing 3D surfaces, whi...

DeepMesh: Differentiable Iso-Surface Extraction

Geometric Deep Learning has recently made striking progress with the adv...

RigNet: Neural Rigging for Articulated Characters

We present RigNet, an end-to-end automated method for producing animatio...

Grasping Field: Learning Implicit Representations for Human Grasps

In recent years, substantial progress has been made on robotic grasping ...

Hierarchical Neural Implicit Pose Network for Animation and Motion Retargeting

We present HIPNet, a neural implicit pose network trained on multiple su...

Superpixel Sampling Networks

Superpixels provide an efficient low/mid-level representation of image d...

Predicting Animation Skeletons for 3D Articulated Models via Volumetric Nets

We present a learning method for predicting animation skeletons for inpu...