Research map / Point clouds / Segmentation and detection
Label-Guided Auxiliary Training Improves 3D Object Detector
Yaomin Huang, Xinmei Liu, Yichen Zhu, Zhiyuan Xu, Chaomin Shen, Zhengping Che, Guixu Zhang, Yaxin Peng, Feifei Feng, Jian Tang
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 LG3D auxiliary training to VoteNet | VoteNet · SUN RGB-D | mAP@0.25: 59.1 -> 61.7 | Improved |
| add LG3D to VoteNet | VoteNet · ScanNetV2 | mAP@0.5: 39.9 -> 43.0 | Improved |
| add LG3D to GroupFree3D | GroupFree3D · ScanNetV2 | mAP@0.25: 69.1 -> 70.9 | Improved |
| add LG3D to GroupFree3D | GroupFree3D · SUN RGB-D | mAP@0.5: 45.2 -> 47.5 | Improved |
| add LG3D to PointPillars | PointPillars · KITTI Car moderate | AP_3d: 74.31 -> 76.42 | Improved |
| add LG3D to 3DSSD | 3DSSD · KITTI Car moderate | AP_3d: 79.57 -> 81.47 | Improved |
| add LKM module to VoteNet baseline (ablation) | VoteNet · ScanNetV2 | mAP@0.5: 39.9 -> 41.3 | Improved |
| add LAI module on top of LKM (ablation) | VoteNet+LKM · ScanNetV2 | mAP@0.5: 41.3 -> 43.0 | Improved |
| use two-stage instead of one-stage training (ablation) | VoteNet+LG3D · ScanNetV2 | mAP@0.5: 42.4 -> 43.0 | Improved |
| train VoteNet baseline for more epochs (36 -> 72) (ablation) | VoteNet · ScanNetV2 | mAP@0.25: 62.90 -> 62.50 | No clear effect |
| train GroupFree3D baseline longer (80 -> 160 epochs) (ablation) | GroupFree3D · ScanNetV2 | mAP@0.25: 69.10 -> 68.50 | No clear effect |
| add size augmentation and fake instances (ablation) | VoteNet+LG3D · ScanNetV2 | mAP@0.25: 64.5 -> 65.1 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- 3DSSD — 3DSSD: Point-Based 3D Single Stage Object Detector (CVPR 2020) · better on 3 of 3 shared results
- PointPillars — PointPillars: Fast Encoders for Object Detection From Point Clouds (CVPR 2019) · better on 3 of 3 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
- Seg2Box: 3D Object Detection by Point-Wise Semantics Supervision (AAAI 2025 · similarity 0.87)
- SP3D: Boosting Sparsely-Supervised 3D Object Detection via Accurate Cross-Modal Semantic Prompts (CVPR 2025 · similarity 0.87)
- Leveraging Imagery Data with Spatial Point Prior for Weakly Semi-supervised 3D Object Detection (AAAI 2024 · similarity 0.87)
- LabelAny3D: Label Any Object 3D in the Wild (NeurIPS 2025 · similarity 0.86)
- Semi-supervised 3D Object Detection with PatchTeacher and PillarMix (AAAI 2024 · similarity 0.86)
- ImOV3D: Learning Open Vocabulary Point Clouds 3D Object Detection from Only 2D Images (NeurIPS 2024 · 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.
