Human Interaction-Aware 3D Reconstruction from a Single Image

TL;DR

HUG3D is a comprehensive framework that reconstructs high-fidelity, physically plausible 3D human models from a single image by modeling group interactions and leveraging multi-view diffusion and physics-based priors.

Contribution

It introduces a novel holistic approach combining group-level context, multi-view diffusion, and physics-based priors for multi-human 3D reconstruction from a single image.

Findings

Outperforms existing methods in multi-human 3D reconstruction accuracy.

Produces more physically plausible and high-fidelity models.

Effectively resolves occlusions and interaction artifacts.

Abstract

Reconstructing textured 3D human models from a single image is fundamental for AR/VR and digital human applications. However, existing methods mostly focus on single individuals and thus fail in multi-human scenes, where naive composition of individual reconstructions often leads to artifacts such as unrealistic overlaps, missing geometry in occluded regions, and distorted interactions. These limitations highlight the need for approaches that incorporate group-level context and interaction priors. We introduce a holistic method that explicitly models both group- and instance-level information. To mitigate perspective-induced geometric distortions, we first transform the input into a canonical orthographic space. Our primary component, Human Group-Instance Multi-View Diffusion (HUG-MVD), then generates complete multi-view normals and images by jointly modeling individuals and group context to resolve occlusions and proximity. Subsequently, the Human Group-Instance Geometric Reconstruction (HUG-GR) module optimizes the geometry by leveraging explicit, physics-based interaction priors to enforce physical plausibility and accurately model inter-human contact. Finally, the multi-view images are fused into a high-fidelity texture. Together, these components form our complete framework, HUG3D. Extensive experiments show that HUG3D significantly outperforms both single-human and existing multi-human methods, producing physically plausible, high-fidelity 3D reconstructions of interacting people from a single image. Project page: https://jongheean11.github.io/HUG3D_project