Research map / Point clouds / Point cloud classification
SC3K: Self-supervised and Coherent 3D Keypoints Estimation from Rotated, Noisy, and Decimated Point Cloud Data
Mohammad Zohaib, Alessio Del Bue
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 |
|---|---|---|---|
| train with individual loss terms instead of Chamfer Distance (ablation) | SC3K · KeypointNet | Inclusivity and Coverage: +5.02 inclusivity, +19.83 coverage | Improved |
| add separation loss (ablation) | SC3K · KeypointNet | Inclusivity: 63.01 -> 78.44 | Improved |
| add consistency loss (ablation) | SC3K · KeypointNet | DAS: 42.44 -> 74.00 | Improved |
| add pose loss (ablation) | SC3K · KeypointNet | matching error: 0.095 -> 0.056 | Improved |
| add overlap loss (ablation) | SC3K · KeypointNet | Inclusivity: 77.09 -> 78.44 | No clear effect |
| add volume loss (ablation) | SC3K · KeypointNet | Inclusivity: 77.35 -> 78.44 | No clear effect |
| train on randomly rotated point clouds (SC3K_rot) vs canonical-pose test | SC3K · KeypointNet | Coverage: Inclusivity 75.89 -> 78.44, Coverage 95.63 -> 91.53 | Mixed |
Closest papers by meaning
- KeyPose: Category-Level 6D Object Pose Estimation with Self-Adaptive Keypoints (AAAI 2025 · similarity 0.88)
- Sonata: Self-Supervised Learning of Reliable Point Representations (CVPR 2025 · similarity 0.88)
- PSA-SSL: Pose and Size-aware Self-Supervised Learning on LiDAR Point Clouds (CVPR 2025 · similarity 0.88)
- Point-Cache: Test-time Dynamic and Hierarchical Cache for Robust and Generalizable Point Cloud Analysis (CVPR 2025 · similarity 0.88)
- Key-Grid: Unsupervised 3D Keypoints Detection using Grid Heatmap Features (NeurIPS 2024 · similarity 0.88)
- FreePoint: Unsupervised Point Cloud Instance Segmentation (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.
