Research map / Label-efficient and robust learning / Domain adaptation and generalization
Not All Distortions Are Created Equal: Distortion-Selective Domain Adaptation for Point Cloud Quality Assessment
Yangwei Li, Xiaochuan Wang, Xin Shang, Haisheng Li
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 |
|---|---|---|---|
| select target-relevant distortions instead of full-set training (ablation) | DST-PCQA · SJTU-PCQA | SROCC: 0.6346 -> 0.7009 | Improved |
| select target-relevant distortions instead of full-set training (ablation) | DST-PCQA · WPC | SROCC: 0.6510 -> 0.6535 | Improved |
| select target-relevant distortions instead of full-set training (ablation) | DST-PCQA · WPC2.0 | PLCC: 0.5808 -> 0.5793 | No clear effect |
| DADS selection instead of random selection at same ratio (ablation) | DST-PCQA · SJTU-PCQA | SROCC: 0.5940 -> 0.7009 | Improved |
| DADS selection instead of random selection at same ratio (ablation) | DST-PCQA · WPC2.0 | SROCC: 0.4745 -> 0.5576 | Improved |
| distortion-selective training applied to MM-PCQA (ablation) | MM-PCQA · SJTU-PCQA | SROCC: 0.5384 -> 0.6418 | Improved |
| distortion-selective training applied to MM-PCQA (ablation) | MM-PCQA · WPC | PLCC: 0.6231 -> 0.6219 | No clear effect |
| distortion-selective training applied to PST-PCQA (ablation) | PST-PCQA · WPC2.0 | SROCC: 0.0067 -> 0.1523 | Improved |
| distortion-selective training applied to PST-PCQA (ablation) | PST-PCQA · WPC2.0 | PLCC: 0.0274 -> 0.1129 | Improved |
| fuse 2D and 3D branches in distortion classifier (ablation) | DADS classifier · LS-PCQA test | accuracy: 86.02% -> 90.86% | Improved |
| raise selection threshold above tau=1/k (ablation) | DADS · WPC | SROCC/PLCC | Hurt |
Closest papers by meaning
- Contrastive Pre-Training with Multi-View Fusion for No-Reference Point Cloud Quality Assessment (CVPR 2024 · similarity 0.91)
- CLIP-PCQA: Exploring Subjective-Aligned Vision-Language Modeling for Point Cloud Quality Assessment (AAAI 2025 · similarity 0.89)
- Learning Disentangled Representations for Perceptual Point Cloud Quality Assessment via Mutual Information Minimization (NeurIPS 2024 · similarity 0.88)
- Bridging the Synthetic-to-Authentic Gap: Distortion-Guided Unsupervised Domain Adaptation for Blind Image Quality Assessment (CVPR 2024 · similarity 0.85)
- Point Cloud Dataset Distillation (ICML 2025 · similarity 0.84)
- DAPoinTr: Domain Adaptive Point Transformer for Point Cloud Completion (AAAI 2025 · similarity 0.84)
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.
