TeHOR: Text-Guided 3D Human and Object Reconstruction with Textures

TL;DR

TeHOR is a novel framework that improves 3D human and object reconstruction from a single image by integrating text descriptions and appearance cues, enabling accurate, semantically coherent, and non-contact interaction modeling.

Contribution

It introduces a text-guided approach that incorporates semantic and appearance cues, addressing limitations of contact-based methods for holistic 3D reconstruction.

Findings

Achieves state-of-the-art reconstruction accuracy.

Effectively models non-contact human-object interactions.

Produces semantically coherent and visually plausible 3D reconstructions.

Abstract

Joint reconstruction of 3D human and object from a single image is an active research area, with pivotal applications in robotics and digital content creation. Despite recent advances, existing approaches suffer from two fundamental limitations. First, their reconstructions rely heavily on physical contact information, which inherently cannot capture non-contact human-object interactions, such as gazing at or pointing toward an object. Second, the reconstruction process is primarily driven by local geometric proximity, neglecting the human and object appearances that provide global context crucial for understanding holistic interactions. To address these issues, we introduce TeHOR, a framework built upon two core designs. First, beyond contact information, our framework leverages text descriptions of human-object interactions to enforce semantic alignment between the 3D reconstruction and its textual cues, enabling reasoning over a wider spectrum of interactions, including non-contact cases. Second, we incorporate appearance cues of the 3D human and object into the alignment process to capture holistic contextual information, thereby ensuring visually plausible reconstructions. As a result, our framework produces accurate and semantically coherent reconstructions, achieving state-of-the-art performance.