Skip to Main content Skip to Navigation
New interface
Conference papers

Neural Human Deformation Transfer

Jean Basset 1, 2 Adnane Boukhayma 2, 3 Stefanie Wuhrer 1 Franck Multon 2, 3 Edmond Boyer 1 
1 MORPHEO - Capture and Analysis of Shapes in Motion
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, Grenoble INP - Institut polytechnique de Grenoble - Grenoble Institute of Technology
2 MIMETIC - Analysis-Synthesis Approach for Virtual Human Simulation
UR2 - Université de Rennes 2, Inria Rennes – Bretagne Atlantique , IRISA-D6 - MEDIA ET INTERACTIONS
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 assume a human pose model to be available and transfer poses between characters using this model. 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 isometryinvariant 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.
Document type :
Conference papers
Complete list of metadata


https://hal.archives-ouvertes.fr/hal-03440562
Contributor : Jean Basset Connect in order to contact the contributor
Submitted on : Monday, November 22, 2021 - 5:12:47 PM
Last modification on : Thursday, September 1, 2022 - 4:04:38 AM
Long-term archiving on: : Wednesday, February 23, 2022 - 8:53:35 PM

Identifiers

  • HAL Id : hal-03440562, version 1

Citation

Jean Basset, Adnane Boukhayma, Stefanie Wuhrer, Franck Multon, Edmond Boyer. Neural Human Deformation Transfer. 3DV 2021 - 9th International Conference on 3D Vision, Dec 2021, Londres (on line event), United Kingdom. pp.1-12. ⟨hal-03440562⟩

Share

Metrics

Record views

146

Files downloads

114