Temporal Residual Jacobians For Rig-free Motion Transfer

TL;DR

This paper presents Temporal Residual Jacobians, a novel data-driven method for rig-free, temporally consistent motion transfer that can generate realistic animations without requiring rigging or keyframes.

Contribution

It introduces a new neural network-based approach that predicts local geometric and temporal changes for motion transfer without intermediate shape keyframes.

Findings

Outperforms state-of-the-art methods in generating realistic animations

Works on diverse synthetic and scanned meshes

Produces geometrically and temporally consistent motions

Abstract

We introduce Temporal Residual Jacobians as a novel representation to enable data-driven motion transfer. Our approach does not assume access to any rigging or intermediate shape keyframes, produces geometrically and temporally consistent motions, and can be used to transfer long motion sequences. Central to our approach are two coupled neural networks that individually predict local geometric and temporal changes that are subsequently integrated, spatially and temporally, to produce the final animated meshes. The two networks are jointly trained, complement each other in producing spatial and temporal signals, and are supervised directly with 3D positional information. During inference, in the absence of keyframes, our method essentially solves a motion extrapolation problem. We test our setup on diverse meshes (synthetic and scanned shapes) to demonstrate its superiority in generating realistic and natural-looking animations on unseen body shapes against SoTA alternatives. Supplemental video and code are available at https://temporaljacobians.github.io/ .