Research map / Detection and segmentation / 3D detection and driving
Interactive 3D Object Detection with Prompts
Ruifei Zhang, Xiangru Lin, Wei Zhang, Jincheng Lu, Xuekuan Wang, Xiao Tan, Yingying Li, Errui Ding, Jingdong Wang, Guanbin Li
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 prompt query position encoding (ablation) | interactive 3D detector · nuScenes val | NDS: 73.5 -> 74.5 | Improved |
| add prompt context embedding from pooled box features (ablation) | interactive 3D detector · nuScenes val | NDS: 74.5 -> 75.0 | Improved |
| add attribute refinement record to Q3D (ablation) | iterative refinement · nuScenes val iteration 1 | NDS: 83.2 -> 84.4 | Improved |
| use global-to-local cross-attention instead of global only (ablation) | decoder · nuScenes val | NDS: 73.7 -> 75.0 | Improved |
| use global-to-local instead of local only (ablation) | decoder · nuScenes val | NDS: 74.3 -> 75.0 | Improved |
| use learned self-correction refinement instead of manual attribute correction on CMT outputs | CMT predictions · nuScenes val | NDS: 86.3 -> 90.4 (R5) | Improved |
| prompt-based interactive annotation versus manual-only annotation | annotation workflow · nuScenes val | time per image (s): 124 -> 55 | Improved |
| add repeated refinement iterations R1 to R5 (ablation) | interactive detector from raw data · nuScenes val | NDS: 75.0 -> 90.5 | Improved |
Closest papers by meaning
- Prompt3D: Random Prompt Assisted Weakly-Supervised 3D Object Detection (CVPR 2024 · similarity 0.89)
- ImOV3D: Learning Open Vocabulary Point Clouds 3D Object Detection from Only 2D Images (NeurIPS 2024 · similarity 0.89)
- SP3D: Boosting Sparsely-Supervised 3D Object Detection via Accurate Cross-Modal Semantic Prompts (CVPR 2025 · similarity 0.89)
- PromptDet: A Lightweight 3D Object Detection Framework with LiDAR Prompts (AAAI 2025 · similarity 0.87)
- LabelAny3D: Label Any Object 3D in the Wild (NeurIPS 2025 · similarity 0.87)
- AGILE3D: Attention Guided Interactive Multi-object 3D Segmentation (ICLR 2024 · similarity 0.87)
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.
