imGHUM: Implicit Generative Models of 3D Human Shape and Articulated Pose

TL;DR

imGHUM introduces a novel implicit 3D human model using signed distance functions, capturing detailed pose, shape, and semantics without explicit templates, enabling high-resolution queries and correspondence tasks.

Contribution

The paper presents the first holistic implicit generative model of 3D human shape and pose, with a new architecture and learning paradigm for detailed, semantic, and high-resolution human modeling.

Findings

Achieves state-of-the-art accuracy in human shape and pose generation

Enables correspondence and semantic understanding between different human models

Supports arbitrary resolution queries for detailed human representations

Abstract

We present imGHUM, the first holistic generative model of 3D human shape and articulated pose, represented as a signed distance function. In contrast to prior work, we model the full human body implicitly as a function zero-level-set and without the use of an explicit template mesh. We propose a novel network architecture and a learning paradigm, which make it possible to learn a detailed implicit generative model of human pose, shape, and semantics, on par with state-of-the-art mesh-based models. Our model features desired detail for human models, such as articulated pose including hand motion and facial expressions, a broad spectrum of shape variations, and can be queried at arbitrary resolutions and spatial locations. Additionally, our model has attached spatial semantics making it straightforward to establish correspondences between different shape instances, thus enabling applications that are difficult to tackle using classical implicit representations. In extensive experiments, we demonstrate the model accuracy and its applicability to current research problems.