Research map / 3D vision / 3D generation
TeHOR: Text-Guided 3D Human and Object Reconstruction with Textures
Hyeongjin Nam, Daniel Sungho Jung, Kyoung Mu Lee
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| condition appearance loss on text prompts (ablation) | TeHOR · Open3DHOI | CD object (cm): 20.348 -> 16.701 | Improved |
| condition appearance loss on text prompts (ablation) | TeHOR · Open3DHOI | Collision: 0.052 -> 0.047 | No clear effect |
| add appearance loss (SDS) (ablation) | TeHOR · Open3DHOI | CD object (cm): 22.094 -> 16.701 | Improved |
| add contact loss (ablation) | TeHOR · Open3DHOI | Contact F1: 0.374 -> 0.412 | Improved |
| add contact loss (ablation) | TeHOR · Open3DHOI | CD object (cm): 19.849 -> 16.701 | Improved |
| use diffusion SDS appearance loss instead of CLIP loss (ablation) | TeHOR · Open3DHOI | CD object (cm): 18.504 -> 16.701 | Improved |
| use 3D Gaussians instead of mesh (ablation) | TeHOR · Open3DHOI | CD object (cm): 25.162 -> 16.701 | Improved |
| add 2D background in rendering (ablation) | TeHOR · Open3DHOI | CD object (cm): 18.196 -> 16.701 | Improved |
| add background in rendering (ablation) | TeHOR · Open3DHOI | Collision: 0.049 -> 0.047 | No clear effect |
| TeHOR vs InteractVLM on non-contact scenes | TeHOR · Open3DHOI (non-contact subset) | CD object (cm): 46.819 -> 17.546 | Improved |
| TeHOR vs InteractVLM on BEHAVE collision | TeHOR · BEHAVE | Collision: 0.021 -> 0.016 (InteractVLM vs TeHOR); HOI-Gaussian 0.019 | Mixed |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- InteractVLM — InteractVLM: 3D Interaction Reasoning from 2D Foundational Models (CVPR 2025) · better on 7 of 7 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- InteractAnything: Zero-shot Human Object Interaction Synthesis via LLM Feedback and Object Affordance Parsing (CVPR 2025 · similarity 0.88)
- Joint Reconstruction of 3D Human and Object via Contact-Based Refinement Transformer (CVPR 2024 · similarity 0.88)
- PICO: Reconstructing 3D People In Contact with Objects (CVPR 2025 · similarity 0.87)
- UniCon3R: Unified Contact-aware 4D Human-Scene Reconstruction from Monocular Video (NeurIPS 2026 · similarity 0.87)
- ChatPose: Chatting about 3D Human Pose (CVPR 2024 · similarity 0.86)
- Reconstructing In-the-Wild Open-Vocabulary Human-Object Interactions (CVPR 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
