Jean Basset, Adnane Boukhayma, Stefanie Wuhrer, Franck Multon and Edmond Boyer

We consider the problem of human deformation transfer, where the goal is to retarget poses between different charac- ters. Traditional methods that tackle this problem require a clear definition of the pose, and use this definition to trans- fer poses between characters. In this work, we take a dif- ferent approach and transform the identity of a character to a new identity without modifying the character’s pose. This offers the advantage of not having to define equivalences of 3D human poses, which is not straight forward as poses tend to change depending on the identity of the character performing it, and as their meaning is highly contextual. To achieve the deformation transfer, we propose a neural encoder-decoder architecture where only identity informa- tion is encoded and where the decoder is conditioned on the pose. We use pose independent representations, such as isometry-invariant shape characteristics, to encode identity features. Our model uses these features to predict 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 com- petitive results for extreme identities, and allows to transfer simple clothing.