Research map / Point clouds / Point cloud classification
DSP-PCQA: Integrating Multiple Perception Preferences for Point Cloud Quality Assessment
Mingxuan Li, Fazhan Zhang, Zhenzhe Hou, Zihao Huang, Bohan Fu, Runze Hu, Xiaohui Chu
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 DFE-based pretraining (both technical and semantic focus) to DSP-PCQA (ablation) | DSP-PCQA · SJTU-PCQA | SRCC: 0.912 -> 0.951 | Improved |
| add semantic-focus pretraining on top of technical-only (ablation) | DSP-PCQA · SJTU-PCQA | SRCC: 0.937 -> 0.951 | Improved |
| add CACA module (context + attribute attention) (ablation) | DSP-PCQA · SJTU-PCQA | SRCC: 0.911 -> 0.951 | Improved |
| use only context correlation (vs both) in CACA (ablation) | DSP-PCQA · SJTU-PCQA | SRCC: 0.951 -> 0.928 | Hurt |
| add EPI token exchange module (ablation) | DSP-PCQA · SJTU-PCQA | SRCC: 0.929 -> 0.951 | Improved |
| add EPI module (PLCC) (ablation) | DSP-PCQA · SJTU-PCQA | PLCC: 0.951 -> 0.964 | Improved |
| fuse technical and semantic streams vs technical stream only (ablation) | DSP-PCQA · SJTU-PCQA | SRCC: 0.936 -> 0.951 | Improved |
| semantic stream vs technical stream on same-distortion subsets | DSP-PCQA streams · SJTU-PCQA per distortion | SRCC: OT 0.857 (Tec) vs 0.922 (Sem); DS+GGN 0.958 vs 0.943 | Mixed |
| train on SJTU test on WPC: DSP-PCQA vs LMM-PCQA | DSP-PCQA · cross-dataset SJTU->WPC | SRCC: 0.475 -> 0.595 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- CLIP-PCQA — CLIP-PCQA: Exploring Subjective-Aligned Vision-Language Modeling for Point Cloud Quality Assessment (AAAI 2025) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- CLIP-PCQA: Exploring Subjective-Aligned Vision-Language Modeling for Point Cloud Quality Assessment (AAAI 2025 · similarity 0.91)
- Learning Disentangled Representations for Perceptual Point Cloud Quality Assessment via Mutual Information Minimization (NeurIPS 2024 · similarity 0.87)
- Contrastive Pre-Training with Multi-View Fusion for No-Reference Point Cloud Quality Assessment (CVPR 2024 · similarity 0.87)
- PerceptionRubrics: Calibrating Multimodal Evaluation to Human Perception (ICML 2026 · similarity 0.84)
- FoMo: Forking Moment in Generative Trajectory as a Perceptual Distance (NeurIPS 2026 · similarity 0.84)
- Multidimensional Observer Model and Perceptual Dimensions of Human Image Quality Assessment (NeurIPS 2026 · 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.
