![[2602.19679] TeHOR: Text-Guided 3D Human and Object Reconstruction with Textures](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2602.19679] TeHOR: Text-Guided 3D Human and Object Reconstruction with Textures
Summary
TeHOR introduces a novel framework for 3D human and object reconstruction using text descriptions, addressing limitations in current methods by enhancing semantic alignment and incorporating appearance cues.
Why It Matters
This research is significant as it advances the field of computer vision by enabling more accurate and context-aware 3D reconstructions, which are essential for applications in robotics and digital content creation. By overcoming limitations of existing methods, TeHOR opens new avenues for understanding human-object interactions.
Key Takeaways
- TeHOR leverages text descriptions to enhance 3D reconstruction accuracy.
- The framework addresses limitations of existing methods by incorporating non-contact interactions.
- It integrates appearance cues for holistic understanding of human-object interactions.
- Achieves state-of-the-art performance in 3D reconstruction tasks.
- Significant implications for robotics and digital content creation.
Computer Science > Computer Vision and Pattern Recognition arXiv:2602.19679 (cs) [Submitted on 23 Feb 2026] Title:TeHOR: Text-Guided 3D Human and Object Reconstruction with Textures Authors:Hyeongjin Nam, Daniel Sungho Jung, Kyoung Mu Lee View a PDF of the paper titled TeHOR: Text-Guided 3D Human and Object Reconstruction with Textures, by Hyeongjin Nam and 2 other authors View PDF HTML (experimental) 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 a...