Research map / Point clouds / Shape and surface completion
R3-PCQA: Ray-Reprojection-Reinforcement for No-Reference 3D Point Cloud Quality Assessment
Junhyuk Seo, Sanghyuk Seo, Dawoon Kim, Heeseok Oh
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 3D point cloud input to 2D image input (ablation) | R3-PCQA · WPC | SRCC: 0.8868 -> 0.9017 | Improved |
| add 2D image input to point cloud input (ablation) | R3-PCQA · WPC | SRCC: 0.7334 -> 0.9017 | Improved |
| add local view quality loss, then policy loss, to global loss (ablation) | R3-PCQA · WPC | SRCC: 0.8644 -> 0.9017 | Improved |
| use RL-selected single subcloud instead of fusing all 9 subclouds (910 points) (ablation) | R3-PCQA · WPC | SRCC: 0.8846 -> 0.9017 | Improved |
| use RL-selected subcloud instead of fusing all 9 full subclouds (8192 points) (ablation) | R3-PCQA · WPC | GFLOPs: 479.32 -> 232.36 | Improved |
| use RL-selected subcloud instead of Fusion-910 on compute (ablation) | R3-PCQA · WPC | GFLOPs: 182.93 -> 232.36 | Hurt |
| train on WPC and test on other datasets | R3-PCQA vs MM-PCQA · Cross-dataset PLCC | PLCC: 0.861 -> 0.920 (WPC2.0); 0.682 -> 0.721 (SJTU) | Improved |
| train on the small SJTU dataset and test on WPC | R3-PCQA vs MM-PCQA · Cross-dataset PLCC | PLCC: 0.351 -> 0.273 | Hurt |
Closest papers by meaning
- CLIP-PCQA: Exploring Subjective-Aligned Vision-Language Modeling for Point Cloud Quality Assessment (AAAI 2025 · similarity 0.88)
- Contrastive Pre-Training with Multi-View Fusion for No-Reference Point Cloud Quality Assessment (CVPR 2024 · similarity 0.88)
- Learning Disentangled Representations for Perceptual Point Cloud Quality Assessment via Mutual Information Minimization (NeurIPS 2024 · similarity 0.87)
- Depth-Guided Robust and Fast Point Cloud Fusion NeRF for Sparse Input Views (AAAI 2024 · similarity 0.85)
- 3DMambaIPF: A State Space Model for Iterative Point Cloud Filtering via Differentiable Rendering (AAAI 2025 · similarity 0.85)
- PointMAC: Meta-Learned Adaptation for Robust Test-Time Point Cloud Completion (NeurIPS 2025 · similarity 0.85)
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.
