Structured Local Radiance Fields for Human Avatar Modeling
This addresses the problem of automated avatar creation for applications like virtual reality or gaming, though it appears incremental as it builds on existing neural rendering techniques.
The paper tackles the challenge of creating animatable clothed human avatars from RGB videos, particularly for loose clothes, by introducing a representation based on structured local radiance fields anchored to a human body template, enabling realistic image generation for novel poses and outperforming state-of-the-art methods.
It is extremely challenging to create an animatable clothed human avatar from RGB videos, especially for loose clothes due to the difficulties in motion modeling. To address this problem, we introduce a novel representation on the basis of recent neural scene rendering techniques. The core of our representation is a set of structured local radiance fields, which are anchored to the pre-defined nodes sampled on a statistical human body template. These local radiance fields not only leverage the flexibility of implicit representation in shape and appearance modeling, but also factorize cloth deformations into skeleton motions, node residual translations and the dynamic detail variations inside each individual radiance field. To learn our representation from RGB data and facilitate pose generalization, we propose to learn the node translations and the detail variations in a conditional generative latent space. Overall, our method enables automatic construction of animatable human avatars for various types of clothes without the need for scanning subject-specific templates, and can generate realistic images with dynamic details for novel poses. Experiment show that our method outperforms state-of-the-art methods both qualitatively and quantitatively.