Hierarchical Neural Implicit Pose Network for Animation and Motion Retargeting

TL;DR

HIPNet is a hierarchical neural implicit pose network that enables flexible motion retargeting and animation by disentangling subject-specific and pose-specific details without relying on ground-truth SDFs or traditional skinning methods.

Contribution

The paper introduces HIPNet, a novel hierarchical neural implicit model that learns a signed distance function from posed skeletons and point clouds, allowing for effective motion retargeting and animation.

Findings

Achieves state-of-the-art results on multiple benchmarks.

Can retarget motion between different subjects.

Supports animation through latent space interpolation.

Abstract

We present HIPNet, a neural implicit pose network trained on multiple subjects across many poses. HIPNet can disentangle subject-specific details from pose-specific details, effectively enabling us to retarget motion from one subject to another or to animate between keyframes through latent space interpolation. To this end, we employ a hierarchical skeleton-based representation to learn a signed distance function on a canonical unposed space. This joint-based decomposition enables us to represent subtle details that are local to the space around the body joint. Unlike previous neural implicit method that requires ground-truth SDF for training, our model we only need a posed skeleton and the point cloud for training, and we have no dependency on a traditional parametric model or traditional skinning approaches. We achieve state-of-the-art results on various single-subject and multi-subject benchmarks.