Research map / Point clouds / Shape and surface completion
MPED: Quantifying Point Cloud Distortion Based on Multiscale Potential Energy Discrepancy
Qi Yang, Yujie Zhang, Siheng Chen, Yiling Xu, Jun Sun, Zhan Ma
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 |
|---|---|---|---|
| use MPED (p=2) instead of EPES | point cloud quality metric · SJTU-PCQA (all impairments) | PLCC: 0.89 -> 0.90 | Improved |
| use MPED (p=2) instead of EPES | point cloud quality metric · SJTU-PCQA (all impairments) | RMSE: 1.12 -> 1.08 | Improved |
| use MPED (p=2) instead of PCQM | point cloud quality metric · SJTU-PCQA (all impairments) | PLCC: 0.86 -> 0.90 | Improved |
| use MPED (p=2) instead of p2point (M) | point cloud quality metric · SJTU-PCQA (all impairments) | PLCC: 0.73 -> 0.90 | Improved |
| use p=2 norm instead of p=1 in MPED (ablation) | MPED · SJTU-PCQA (all impairments) | SROCC: 0.88 -> 0.89 | Improved |
| use p=2 norm instead of p=1 in MPED (ablation) | MPED · SJTU-PCQA (all impairments) | PLCC: 0.90 -> 0.90 | No clear effect |
| use p=2 norm instead of p=1 in MPED (ablation) | MPED · SJTU-PCQA (OT impairment) | SROCC: 0.68 -> 0.76 | Improved |
| use p=2 norm instead of p=1 in MPED (ablation) | MPED · SJTU-PCQA (D+C impairment) | PLCC: 0.95 -> 0.97 | Improved |
| use neighborhood size K=10 PED instead of CD (K=1) as reconstruction loss | LatentNet · point cloud reconstruction (qualitative) | isolated points | Improved |
Closest papers by meaning
- Learning Disentangled Representations for Perceptual Point Cloud Quality Assessment via Mutual Information Minimization (NeurIPS 2024 · similarity 0.86)
- Learning Continuous Implicit Field with Local Distance Indicator for Arbitrary-Scale Point Cloud Upsampling (AAAI 2024 · similarity 0.84)
- NeuroGauss4D-PCI: 4D Neural Fields and Gaussian Deformation Fields for Point Cloud Interpolation (NeurIPS 2024 · similarity 0.84)
- CLIP-PCQA: Exploring Subjective-Aligned Vision-Language Modeling for Point Cloud Quality Assessment (AAAI 2025 · similarity 0.84)
- APML: Adaptive Probabilistic Matching Loss for Robust 3D Point Cloud Reconstruction (NeurIPS 2025 · similarity 0.84)
- Contrastive Pre-Training with Multi-View Fusion for No-Reference Point Cloud Quality Assessment (CVPR 2024 · similarity 0.83)
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.
