SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2207.09193 · ECCV · 2022

NDF: Neural Deformable Fields for Dynamic Human Modelling

Jie Chen, Ruiqi Zhang

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2207.09193")
get_code_for_paper("2207.09193")
have("2207.09193")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2207.09193.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2207.09193.svg)](https://syntology.ai/paper/2207.09193)

Connect an agent — have() is free.