@inproceedings{07872fe33462495995eb2b6f82abbc40,
title = "NDF: Neural Deformable Fields for Dynamic Human Modelling",
abstract = "We propose Neural Deformable Fields (NDF), a new representation for dynamic human digitization from a multi-view video. Recent works proposed to represent a dynamic human body with shared canonical neural radiance fields which links to the observation space with deformation fields estimations. However, the learned canonical representation is static and the current design of the deformation fields is not able to represent large movements or detailed geometry changes. In this paper, we propose to learn a neural deformable field wrapped around a fitted parametric body model to represent the dynamic human. The NDF is spatially aligned by the underlying reference surface. A neural network is then learned to map pose to the dynamics of NDF. The proposed NDF representation can synthesize the digitized performer with novel views and novel poses with a detailed and reasonable dynamic appearance. Experiments show that our method significantly outperforms recent human synthesis methods.",
keywords = "Neural implicit representation, Volumetric rendering, Novel view synthesis, Dynamic motion, Human shape and appearance modelling",
author = "Ruiqi Zhang and Jie Chen",
note = "Funding Information: The research was supported by the Theme-based Research Scheme, Research Grants Council of Hong Kong (T45-205/21-N). Publisher copyright: {\textcopyright} 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG",
year = "2022",
month = nov,
day = "12",
doi = "10.1007/978-3-031-19824-3_3",
language = "English",
isbn = "9783031198236",
series = "Lecture Notes in Computer Science",
publisher = "Springer Cham",
pages = "37--52",
editor = "Shai Avidan and Gabriel Brostow and Moustapha Ciss{\'e} and Farinella, {Giovanni Maria} and Tal Hassner",
booktitle = "Computer Vision – ECCV 2022",
edition = "1st",
}