Temporal Residual Jacobians For Rig-free Motion Transfer
This addresses motion transfer for animation and graphics, enabling realistic animations on unseen body shapes without rigging, though it appears incremental as it builds on data-driven methods.
The paper tackles the problem of motion transfer without requiring rigging or keyframes by introducing Temporal Residual Jacobians, achieving geometrically and temporally consistent animations on diverse meshes and outperforming state-of-the-art alternatives.
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/ .