NDF: Neural Deformable Fields for Dynamic Human Modelling

TL;DR

This paper introduces Neural Deformable Fields (NDF), a novel dynamic human modeling method that captures detailed geometry changes and large movements from multi-view videos, enabling realistic synthesis of humans in new poses and views.

Contribution

NDF is a new neural representation that models dynamic humans with spatially aligned deformable fields around a parametric body, improving detail and movement representation over prior static canonical models.

Findings

Outperforms recent human synthesis methods

Enables realistic novel view and pose synthesis

Captures detailed geometry and large movements

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.