Research map / Image generation / Image restoration
Blindly Assess Image Quality in the Wild Guided by a Self-Adaptive Hyper Network
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 |
|---|---|---|---|
| use the self-adaptive hyper network with local distortion features | BIQA model · LIVEC | SRCC: 0.857 -> 0.859 | Helped |
| use the self-adaptive hyper network with local distortion features | BIQA model · BID | SRCC: 0.845 -> 0.869 | Helped |
| use the self-adaptive hyper network with local distortion features | BIQA model · KonIQ-10k | SRCC: 0.880 -> 0.906 | Helped |
| use the self-adaptive hyper network with local distortion features | BIQA model · LIVE | SRCC: 0.968 -> 0.962 | Hurt |
| use the self-adaptive hyper network with local distortion features | BIQA model · CSIQ | SRCC: 0.955 -> 0.923 | Hurt |
| add the local distortion aware module and hyper network (ablation) | ResNet-50 BIQA · LIVEC | SRCC: 0.827 -> 0.859 | Helped |
| add the local distortion aware module and hyper network (ablation) | ResNet-50 BIQA · LIVE | SRCC: 0.923 -> 0.962 | Helped |
| add the hyper network (ablation) | ResNet-50 with multi-scale features · LIVEC | SRCC: 0.836 -> 0.859 | Helped |
| add the hyper network (ablation) | ResNet-50 with multi-scale features · LIVE | SRCC: 0.954 -> 0.962 | Helped |
| add multi-scale local distortion features (ablation) | ResNet-50 with hyper network · LIVEC | SRCC: 0.854 -> 0.859 | Helped |
| add multi-scale local distortion features (ablation) | ResNet-50 with hyper network · LIVE | SRCC: 0.944 -> 0.962 | Helped |
Closest papers by meaning
- Bridging the Synthetic-to-Authentic Gap: Distortion-Guided Unsupervised Domain Adaptation for Blind Image Quality Assessment (CVPR 2024 · similarity 0.89)
- Distilling Spatially-Heterogeneous Distortion Perception for Blind Image Quality Assessment (CVPR 2025 · similarity 0.89)
- Integrating Global Context Contrast and Local Sensitivity for Blind Image Quality Assessment (ICML 2024 · similarity 0.88)
- Towards Syn-to-Real IQA: A Novel Perspective on Reshaping Synthetic Data Distributions (NeurIPS 2025 · similarity 0.88)
- Semi-Supervised Blind Image Quality Assessment through Knowledge Distillation and Incremental Learning (AAAI 2024 · similarity 0.86)
- Toward Generalized Image Quality Assessment: Relaxing the Perfect Reference Quality Assumption (CVPR 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.