Research map / Image generation / Autoregressive and latent generation
Blind Multimodal Quality Assessment of Low-Light Images
Miaohui Wang, Zhuowei Xu, Mai Xu, Weisi Lin
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 multimodal self-supervised alignment stage to image-only model (ablation) | BMQA RN-50 · MLIQ | PLCC: 0.7964 -> 0.8567 | Improved |
| add multimodal self-supervised alignment stage to text-only model (ablation) | BMQA TransF · MLIQ | PLCC: 0.7504 -> 0.8209 | Improved |
| add text modality to supervised stage (image+text instead of image only) (ablation) | BMQA RN-50 · MLIQ | PLCC: 0.8567 -> 0.8614 | Improved |
| add feature-alignment pre-training on MS-COCO (ablation) | BMQA RN-50 + TransF · MLIQ | PLCC: 0.8614 -> 0.8989 | Improved |
| use feature-alignment pre-training instead of classification pre-training (ablation) | BMQA RN-50 + TransF · MLIQ | PLCC: 0.8707 -> 0.8989 | Improved |
| use feature-alignment pre-training instead of restoration pre-training (ablation) | BMQA RN-50 + TransF · MLIQ | PLCC: 0.8753 -> 0.8989 | Improved |
| use image modality instead of text modality alone (ablation) | BMQA · MLIQ | PLCC: 0.7504 -> 0.7964 | Improved |
| use Transformer text encoder instead of bag-of-words | BMQA CNXT-B · MLIQ | PLCC: 0.8822 -> 0.9121 | Improved |
| use ConvNeXT-B image encoder instead of VGG-19 | BMQA TransF · MLIQ | PLCC: 0.8731 -> 0.9121 | Improved |
| replace ResNet-152 with lighter ResNet-18 | BMQA · MLIQ | PLCC: 0.8863 to 0.9025 | No clear effect |
| use BMQA CNXT-B + TransF instead of best hand-crafted/deep BIQA | BMQA · MLIQ entire database | PLCC: 0.8596 -> 0.9121 | Improved |
Closest papers by meaning
- Integrating Global Context Contrast and Local Sensitivity for Blind Image Quality Assessment (ICML 2024 · similarity 0.89)
- Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Vision (ICLR 2024 · similarity 0.87)
- Distilling Spatially-Heterogeneous Distortion Perception for Blind Image Quality Assessment (CVPR 2025 · similarity 0.86)
- Feature Denoising Diffusion Model for Blind Image Quality Assessment (AAAI 2025 · similarity 0.86)
- Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Compare (NeurIPS 2024 · similarity 0.86)
- Semi-Supervised Blind Image Quality Assessment through Knowledge Distillation and Incremental Learning (AAAI 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.
