Research map / Detection and segmentation / 3D detection and driving
Global-Local Collaborative Inference with LLM for Lidar-Based Open-Vocabulary Detection
Xingyu Peng, Yan Bai, Chen Gao, Lirong Yang, Fei Xia, Beipeng Mu, Xiaofei Wang, Si Liu
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 Reflected Pseudo Labels Generation (CLIP-based label check) (ablation) | GLIS base model · ScanNetV2 (top-10 classes) | mAP25: 28.59 -> 28.80 | Improved |
| add Reflected Pseudo Labels Generation (ablation) | GLIS base model · ScanNetV2 (top-20 classes) | mAP25: 19.36 -> 19.51 | Improved |
| add Background-Aware Object Localization (ablation) | GLIS with RPLG · ScanNetV2 (top-10 classes) | mAP25: 28.80 -> 29.75 | Improved |
| add Background-Aware Object Localization (ablation) | GLIS with RPLG · ScanNetV2 (top-20 classes) | mAP25: 19.51 -> 20.03 | Improved |
| add global-local collaborative inference with LLM (ablation) | GLIS with RPLG and BAOL · ScanNetV2 (top-10 classes) | mAP25: 29.75 -> 30.94 | Improved |
| add global-local collaborative inference with LLM (ablation) | GLIS with RPLG and BAOL · ScanNetV2 (top-20 classes) | mAP25: 20.03 -> 20.83 | Improved |
| GLIS vs CoDA on ScanNetV2 | CoDA · ScanNetV2 (top-10 classes) | mAP25: 28.76 -> 30.94 | Improved |
| GLIS vs OV-3DET on SUN RGB-D top-20 classes | OV-3DET · SUN RGB-D (top-20 classes) | mAP25: 20.46 -> 21.45 | Improved |
| GLIS vs OV-3DET on SUN RGB-D top-10 classes | OV-3DET · SUN RGB-D (top-10 classes) | mAP25: 31.06 -> 30.83 | No clear effect |
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.
- FM-OV3D — FM-OV3D: Foundation Model-Based Cross-Modal Knowledge Blending for Open-Vocabulary 3D Detection (AAAI 2024) · better on 2 of 2 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
- Training an Open-Vocabulary Monocular 3D Detection Model without 3D Data (NeurIPS 2024 · similarity 0.90)
- 3D-AVS: LiDAR-based 3D Auto-Vocabulary Segmentation (CVPR 2025 · similarity 0.88)
- OW-OVD: Unified Open World and Open Vocabulary Object Detection (CVPR 2025 · similarity 0.88)
- How to Evaluate the Generalization of Detection? A Benchmark for Comprehensive Open-Vocabulary Detection (AAAI 2024 · similarity 0.88)
- LiDAR-LLM: Exploring the Potential of Large Language Models for 3D LiDAR Understanding (AAAI 2025 · similarity 0.88)
- ImOV3D: Learning Open Vocabulary Point Clouds 3D Object Detection from Only 2D Images (NeurIPS 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.
