Research map / Point clouds / Registration and matching
Point Cloud Quality Assessment via Multi-View Structure-Aware Feature Fusion
Jian Xiong, Lingxia Jiang, Xianzhong Long, Miaohui Wang, Hao Gao
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 mask maps as input (ablation) | SAF-Net · WPC | PLCC: 0.853 -> 0.893 | Improved |
| add LBP maps as input (ablation) | SAF-Net · WPC | PLCC: 0.862 -> 0.893 | Improved |
| add texture images as input (ablation) | SAF-Net · WPC | PLCC: 0.877 -> 0.893 | Improved |
| add composite ViT features to individual features (ablation) | SAF-Net · WPC | PLCC: 0.887 -> 0.893 | Improved |
| add individual-feature encoders to composite-only model (ablation) | SAF-Net · WPC | PLCC: 0.828 -> 0.893 | Improved |
| use SAF-Net instead of best prior on LS-PCQA | SAF-Net · LS-PCQA | PLCC: 0.741 -> 0.880 | Improved |
| use SAF-Net instead of CMDC-PCQA on WPC2.0 | SAF-Net · WPC2.0 | PLCC: 0.810 -> 0.896 | Improved |
| train on SJTU-PCQA and test on LS-PCQA | SAF-Net · Cross-dataset SJTU->LS-PCQA | PLCC: 0.331 vs 0.373 (MM-PCQA) | No clear effect |
| use SAF-Net over MM-PCQA in cross-dataset LS-PCQA->SJTU | SAF-Net · Cross-dataset LS-PCQA->SJTU | PLCC: 0.581 -> 0.791 | Improved |
| use SAF-Net over CANet on WPC | SAF-Net · WPC | PLCC: 0.895 vs 0.896 | No clear effect |
Closest papers by meaning
- Contrastive Pre-Training with Multi-View Fusion for No-Reference Point Cloud Quality Assessment (CVPR 2024 · similarity 0.89)
- Learning Disentangled Representations for Perceptual Point Cloud Quality Assessment via Mutual Information Minimization (NeurIPS 2024 · similarity 0.89)
- CLIP-PCQA: Exploring Subjective-Aligned Vision-Language Modeling for Point Cloud Quality Assessment (AAAI 2025 · similarity 0.87)
- Depth-Guided Robust and Fast Point Cloud Fusion NeRF for Sparse Input Views (AAAI 2024 · similarity 0.86)
- 3DMambaIPF: A State Space Model for Iterative Point Cloud Filtering via Differentiable Rendering (AAAI 2025 · similarity 0.86)
- DMF-Net: Image-Guided Point Cloud Completion with Dual-Channel Modality Fusion and Shape-Aware Upsampling Transformer (AAAI 2025 · 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.
