COAP: Compositional Articulated Occupancy of People

TL;DR

This paper introduces COAP, a neural implicit representation for articulated human bodies that improves generalization and efficiency by decomposing geometry into local parts and leveraging shape and kinematic knowledge.

Contribution

The paper proposes a part-aware encoder-decoder architecture for neural implicit bodies, enhancing pose generalization and inference speed over prior methods.

Findings

Outperforms existing methods in accuracy and efficiency

Effectively models complex deformations and local shape constraints

Handles self-intersections and environmental collisions

Abstract

We present a novel neural implicit representation for articulated human bodies. Compared to explicit template meshes, neural implicit body representations provide an efficient mechanism for modeling interactions with the environment, which is essential for human motion reconstruction and synthesis in 3D scenes. However, existing neural implicit bodies suffer from either poor generalization on highly articulated poses or slow inference time. In this work, we observe that prior knowledge about the human body's shape and kinematic structure can be leveraged to improve generalization and efficiency. We decompose the full-body geometry into local body parts and employ a part-aware encoder-decoder architecture to learn neural articulated occupancy that models complex deformations locally. Our local shape encoder represents the body deformation of not only the corresponding body part but also the neighboring body parts. The decoder incorporates the geometric constraints of local body shape which significantly improves pose generalization. We demonstrate that our model is suitable for resolving self-intersections and collisions with 3D environments. Quantitative and qualitative experiments show that our method largely outperforms existing solutions in terms of both efficiency and accuracy. The code and models are available at https://neuralbodies.github.io/COAP/index.html