Research map / 3D vision / 3D generation
OP3DSG: Open-vocabulary Part-aware 3D Scene Graph Generation for Real-world Environments
Yirum Kim, Ue-Hwan Kim
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 |
|---|---|---|---|
| add knowledge-guided control of the entity space (ablation) | OP3DSG · UniGraph3D | Part Node R@3: 45.9 -> 83.6 | Improved |
| add knowledge-guided control of the entity space (ablation) | OP3DSG · UniGraph3D | Affordance R@3: 30.7 -> 76.7 | Improved |
| add knowledge-guided control of the entity space (ablation) | OP3DSG · UniGraph3D | Func. Triplet R@3: 15.5 -> 51.1 | Improved |
| add color-distribution feature for part association (ablation) | OP3DSG · UniGraph3D | Part Node R@3: 79.0 -> 83.6 | Improved |
| add color-distribution feature for part association (ablation) | OP3DSG · UniGraph3D | Func. Triplet R@3: 40.2 -> 51.1 | Improved |
| add color-distribution feature for part association (ablation) | OP3DSG · UniGraph3D | Affordance R@3: 64.8 -> 76.7 | Improved |
| add geometry-initialized prior graph instead of flat node list (ablation) | OP3DSG · UniGraph3D | Func. Triplet R@3: 47.1 -> 51.1 | Improved |
| add geometry-initialized prior graph instead of flat node list (ablation) | OP3DSG · UniGraph3D | Affordance R@3: 74.7 -> 76.7 | Improved |
| decompose reasoning into multiple role-specific LLM agents (ablation) | OP3DSG · UniGraph3D | Func. Triplet R@3: 20.7 -> 51.1 | Improved |
| decompose reasoning into multiple role-specific LLM agents (ablation) | OP3DSG · UniGraph3D | Affordance R@3: 40.8 -> 76.7 | Improved |
| use OP3DSG (no VLM captioning) instead of ConceptGraph pipeline (ablation) | OP3DSG · UniGraph3D (2D detection stage) | peak GPU memory (GB): 11.43 -> 8.08 | Improved |
Closest papers by meaning
- Open3DSG: Open-Vocabulary 3D Scene Graphs from Point Clouds with Queryable Objects and Open-Set Relationships (CVPR 2024 · similarity 0.92)
- Open-Vocabulary Functional 3D Scene Graphs for Real-World Indoor Spaces (CVPR 2025 · similarity 0.90)
- OpenLex3D: A Tiered Benchmark for Open-Vocabulary 3D Scene Representations (NeurIPS 2025 · similarity 0.89)
- Cross-Modal and Uncertainty-Aware Agglomeration for Open-Vocabulary 3D Scene Understanding (CVPR 2025 · similarity 0.89)
- Object-Centric Representation Learning for Enhanced 3D Semantic Scene Graph Prediction (NeurIPS 2025 · similarity 0.89)
- SceneFun3D: Fine-Grained Functionality and Affordance Understanding in 3D Scenes (CVPR 2024 · similarity 0.89)
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.
