Research map / Vision-language and multimodal / Cross-modal learning
Bridging the Perceptual Gap: Residual-Enhanced Downscaling and Manifold-Aware Perception Alignment Adaptation for NR-IQA
Yu Li, Zhengran Shen, Yachun Mi, Puchao Zhou, Shaohui Liu
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 RPD residual-enhanced downsampling to CMPA (ablation) | CMPA · KonIQ-10k | SRCC: 0.935 -> 0.938 | Improved |
| add RPD residual-enhanced downsampling to CMPA (ablation) | CMPA · KADID-10k | SRCC: 0.937 -> 0.938 | Improved |
| add PAI cross-modal interaction on top of PFE (ablation) | CMPA · KADID-10k | SRCC: 0.936 -> 0.938 | Improved |
| add PFE shared MLP to dual text and image tuning (ablation) | CMPA · KADID-10k | SRCC: 0.928 -> 0.936 | Improved |
| tune image encoder adapter in addition to text (ablation) | CMPA · KADID-10k | SRCC: 0.792 -> 0.928 | Improved |
| tune text and image independently vs image only (ablation) | CMPA · KADID-10k | SRCC: 0.928 -> 0.928 | No clear effect |
| use low-dimensional PFE instead of high-dimensional (ablation) | CMPA PFE · KADID-10k | SRCC: 0.912 -> 0.936 | Improved |
| add residual information to bicubic downsampling (ablation) | RPD · TID2013 | SRCC: 0.879 -> 0.870 | Hurt |
| add perceptual weight on top of JND weight map (ablation) | RPD · TID2013 | SRCC: 0.883 -> 0.899 | Improved |
| add RPD preprocessing to HyperIQA | HyperIQA · LIVEC | SRCC: 0.859 -> 0.868 | Improved |
| add RPD preprocessing to MANIQA | MANIQA · LIVEC | SRCC: 0.868 -> 0.870 | Improved |
| use ViT-L-14 backbone instead of ViT-B-16 | CMPA · KADID-10k | SRCC: 0.934 -> 0.951 | Improved |
Closest papers by meaning
- Post-pre-training for Modality Alignment in Vision-Language Foundation Models (CVPR 2025 · similarity 0.88)
- LGDM: Latent Guidance in Diffusion Models for Perceptual Evaluations (ICML 2025 · similarity 0.87)
- Augmenting Perceptual Super-Resolution via Image Quality Predictors (CVPR 2025 · similarity 0.87)
- Unlocking Fine-Grained Perception in CLIP via Structurally-Aware Latent Masked Modeling (NeurIPS 2026 · similarity 0.86)
- Seeing the Image: Prioritizing Visual Correlation by Contrastive Alignment (NeurIPS 2024 · similarity 0.86)
- Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Compare (NeurIPS 2024 · 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.
