NeuWigs: A Neural Dynamic Model for Volumetric Hair Capture and Animation
This addresses the challenge of creating realistic hair animations for virtual reality, which is incremental as it builds on existing data-driven approaches but introduces specific improvements in disentanglement and stability.
The paper tackles the problem of capturing and animating realistic human hair for virtual reality avatars by introducing a two-stage neural dynamic model that outperforms state-of-the-art methods in novel view synthesis and enables novel hair animations without requiring hair observations as input.
The capture and animation of human hair are two of the major challenges in the creation of realistic avatars for the virtual reality. Both problems are highly challenging, because hair has complex geometry and appearance, as well as exhibits challenging motion. In this paper, we present a two-stage approach that models hair independently from the head to address these challenges in a data-driven manner. The first stage, state compression, learns a low-dimensional latent space of 3D hair states containing motion and appearance, via a novel autoencoder-as-a-tracker strategy. To better disentangle the hair and head in appearance learning, we employ multi-view hair segmentation masks in combination with a differentiable volumetric renderer. The second stage learns a novel hair dynamics model that performs temporal hair transfer based on the discovered latent codes. To enforce higher stability while driving our dynamics model, we employ the 3D point-cloud autoencoder from the compression stage for de-noising of the hair state. Our model outperforms the state of the art in novel view synthesis and is capable of creating novel hair animations without having to rely on hair observations as a driving signal. Project page is here https://ziyanw1.github.io/neuwigs/.