Research map / Point clouds / Point cloud classification
No-Reference Point Cloud Quality Assessment via Domain Adaptation
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 the image source domain on TID2013 rather than LIVE | IT-PCQA · WPC | PLCC: 0.31 -> 0.55 | Helped |
| train the image source domain on TID2013 rather than LIVE | IT-PCQA · WPC | SROCC: 0.28 -> 0.54 | Helped |
| fuse hierarchical features with H-SCNN rather than use other tested encoders (ablation) | IT-PCQA · WPC | PLCC: 0.4270 -> 0.5491 | Helped |
| fuse hierarchical features with H-SCNN rather than use other tested encoders (ablation) | IT-PCQA · WPC | SROCC: 0.4276 -> 0.5371 | Helped |
| use six-view multi-perspective images rather than single-perspective input (ablation) | IT-PCQA · SJTU-PCQA (TID2013 to target) | PLCC: 0.4251 -> 0.5791 | Helped |
| use six-view multi-perspective images rather than single-perspective input (ablation) | IT-PCQA · WPC (TID2013 to target) | SROCC: 0.3620 -> 0.5371 | Helped |
| use six-view multi-perspective images rather than single-perspective input (ablation) | IT-PCQA · WPC (LIVE to target) | PLCC: 0.3512 -> 0.3099 | Mixed |
| add conditional adversarial learning with CCEL rather than train with regression loss only (ablation) | IT-PCQA · WPC | PLCC: 0.3870 -> 0.5491 | Helped |
| use conditional adversarial loss rather than conventional adversarial loss (ablation) | IT-PCQA · WPC | PLCC: 0.3125 -> 0.5491 | Helped |
| use conditional adversarial loss rather than MMD loss (ablation) | IT-PCQA · WPC | SROCC: 0.3838 -> 0.5371 | Helped |
| add SROCC loss without effective domain transfer (ablation) | IT-PCQA · WPC | PLCC: 0.3870 -> 0.0272 | Hurt |
| transfer image quality knowledge to point clouds using IT-PCQA instead of GraphSIM | no-reference point cloud assessment · WPC | PLCC: 0.74 -> 0.55 | Hurt |
Closest papers by meaning
- QD-PCQA: Quality-Aware Domain Adaptation for Point Cloud Quality Assessment (CVPR 2026 · similarity 0.92)
- Contrastive Pre-Training with Multi-View Fusion for No-Reference Point Cloud Quality Assessment (CVPR 2024 · similarity 0.91)
- 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 0.89)
- Point Cloud Dataset Distillation (ICML 2025 · similarity 0.86)
- You Should Learn to Stop Denoising on Point Clouds in Advance (AAAI 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.