Research map / Point clouds / Point cloud classification
KeypointDETR: An End-to-End 3D Keypoint Detector
Hairong Jin, Yuefan Shen, Jianwen Lou, Kun Zhou, Youyi Zheng
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 |
|---|---|---|---|
| use bipartite-matching multi-heatmap end-to-end detection instead of shared heatmap with NMS/clustering | KeypointDETR · KeypointNet saliency (avg) | Hungarian mIoU (%): 82.70 -> 93.81 vs Wei et al. | Improved |
| add query-wise transformer decoder instead of MLP decoders (ablation) | KeypointDETR · KeypointNet saliency (avg) | Hungarian mIoU (%): 91.67 -> 93.81 | Improved |
| add position encoding in decoder (ablation) | KeypointDETR · KeypointNet saliency (avg) | Hungarian mIoU (%): 92.47 -> 93.81 | Improved |
| use heatmap-based prediction instead of coordinate-based prediction (ablation) | KeypointDETR · KeypointNet saliency (avg) | Hungarian mIoU (%): 49.83 -> 93.81 | Improved |
| add cascade offset prediction to coordinate-based variant (ablation) | KeypointDETR coordinate-based · KeypointNet saliency (avg) | Hungarian mIoU (%): 49.83 -> 58.81 | Improved |
| use dynamic graph transformer encoder instead of DGCNN encoder (ablation) | KeypointDETR · KeypointNet saliency (avg) | Hungarian mIoU (%): 89.81 -> 93.81 | Improved |
| use dynamic graph transformer encoder instead of PointNet++ or Point Transformer encoder (ablation) | KeypointDETR · KeypointNet saliency (avg) | Hungarian mIoU (%): 73.28 -> 93.81 (PN2); 80.45 -> 93.81 (PT) | Improved |
| replace encoder with pre-trained Point-BERT, Point-MAE or I2P-MAE (ablation) | KeypointDETR · KeypointNet saliency (avg) | Hungarian mIoU (%): 92.88 / 90.88 / 83.57 vs 93.81 | No clear effect |
| use KeypointDETR instead of Wei et al. for correspondence | KeypointDETR · KeypointNet correspondence (avg) | Hungarian mIoU (%): 80.12 -> 87.09 | 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.
- SkeletonMerger — Skeleton Merger: An Unsupervised Aligned Keypoint Detector (CVPR 2021) · better on 1 of 1 shared result
- PointConv — PointConv: Deep Convolutional Networks on 3D Point Clouds (CVPR 2019) · 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
- Key-Grid: Unsupervised 3D Keypoints Detection using Grid Heatmap Features (NeurIPS 2024 · similarity 0.92)
- KeypointDeformer: Unsupervised 3D Keypoint Discovery for Shape Control (CVPR 2021 · similarity 0.90)
- KeypointNet: A Large-Scale 3D Keypoint Dataset Aggregated From Numerous Human Annotations (CVPR 2020 · similarity 0.90)
- Back to 3D: Few-Shot 3D Keypoint Detection with Back-Projected 2D Features (CVPR 2024 · similarity 0.89)
- Unsupervised 3D Structure Inference from Category-Specific Image Collections (CVPR 2024 · similarity 0.88)
- KP-RED: Exploiting Semantic Keypoints for Joint 3D Shape Retrieval and Deformation (CVPR 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.
