Neural Human Deformation Transfer

TL;DR

This paper introduces a neural network approach for human deformation transfer that focuses on changing character identity without modifying pose, avoiding the need for explicit pose definitions and improving generalization.

Contribution

It proposes a pose-conditioned encoder-decoder architecture using pose-independent identity features for deformation transfer, outperforming existing methods.

Findings

Outperforms state-of-the-art methods quantitatively and qualitatively

Generalizes better to unseen poses

Enables transfer of simple clothing and extreme identities

Abstract

We consider the problem of human deformation transfer, where the goal is to retarget poses between different characters. Traditional methods that tackle this problem require a clear definition of the pose, and use this definition to transfer poses between characters. In this work, we take a different approach and transform the identity of a character into a new identity without modifying the character's pose. This offers the advantage of not having to define equivalences between 3D human poses, which is not straightforward as poses tend to change depending on the identity of the character performing them, and as their meaning is highly contextual. To achieve the deformation transfer, we propose a neural encoder-decoder architecture where only identity information is encoded and where the decoder is conditioned on the pose. We use pose independent representations, such as isometry-invariant shape characteristics, to represent identity features. Our model uses these features to supervise the prediction of offsets from the deformed pose to the result of the transfer. We show experimentally that our method outperforms state-of-the-art methods both quantitatively and qualitatively, and generalises better to poses not seen during training. We also introduce a fine-tuning step that allows to obtain competitive results for extreme identities, and allows to transfer simple clothing.