Research map / Detection and segmentation / Open-set and few-shot detection
Unlocking Textual and Visual Wisdom: Open-Vocabulary 3D Object Detection Enhanced by Comprehensive Guidance from Text and Image
Pengkun Jiao, Na Zhao, Jingjing Chen, Yu-Gang Jiang
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 image-guided novel class discovery (IGND) (ablation) | class-agnostic 3DETR · SUN RGB-D | mAR novel: 34.12 -> 51.12 | Improved |
| add IGND without feature alignment (ablation) | 3DETR · SUN RGB-D | mAP base: 4.03 -> 2.07 | Hurt |
| add instance-level 3D-image alignment (ablation) | IGND detector · SUN RGB-D | mAP novel: 0.35 -> 6.85 | Improved |
| add class-level cross-modal alignment (ablation) | IGND + instance alignment · SUN RGB-D | mAP novel: 6.85 -> 8.03 | Improved |
| add scene-level alignment (PISE) (ablation) | IGND + instance + class alignment · SUN RGB-D | mAP novel: 8.03 -> 8.91 | Improved |
| add image-guided query seed initialization (ablation) | IGND · SUN RGB-D | mAR novel: 48.31 -> 51.12 | Improved |
| add instance-level alignment on top of IGND (ablation) | IGND detector · SUN RGB-D | mAR novel: 51.12 -> 50.70 | No clear effect |
| use INHA instead of CoDA | OV-3DDet · SUN RGB-D | mAP novel: 6.71 -> 8.91 | Improved |
| use INHA instead of CoDA | OV-3DDet · ScanNetv2 | mAP novel: 6.54 -> 7.79 | Improved |
| use INHA instead of CoDA across ScanNet-10 classes | OV-3DDet · ScanNet-10 | per-class mAP: 28.76 -> 30.06 average; sink 45.26 -> 35.69 | 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.
- Det-CLIP — DetCLIP: Dictionary-Enriched Visual-Concept Paralleled Pre-training for Open-world Detection (NeurIPS 2022) · better on 1 of 1 shared result
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
- FM-OV3D: Foundation Model-Based Cross-Modal Knowledge Blending for Open-Vocabulary 3D Detection (AAAI 2024 · similarity 0.93)
- Hierarchical Cross-Modal Alignment for Open-Vocabulary 3D Object Detection (AAAI 2025 · similarity 0.92)
- ImOV3D: Learning Open Vocabulary Point Clouds 3D Object Detection from Only 2D Images (NeurIPS 2024 · similarity 0.92)
- Towards 3D Objectness Learning in an Open World (NeurIPS 2025 · similarity 0.91)
- Open-Vocabulary 3D Semantic Segmentation with Foundation Models (CVPR 2024 · similarity 0.91)
- LLMs Meet VLMs: Boost Open Vocabulary Object Detection with Fine-grained Descriptors (ICLR 2024 · similarity 0.90)
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.
