Research map / Image generation / Super-resolution
Burst Image Quality Assessment: A New Benchmark and Unified Framework for Multiple Downstream Tasks
Xiaoye Liang, Lai Jiang, Minglang Qiao, Yichen Guo, Yue Zhang, Xin Deng, Shengxi Li, Yufan Liu, Mai Xu
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 TPG module to the prompt generation network (ablation) | BuIQA framework · BI-OQA ablation | SRCC: 0.500 -> 0.643 | Improved |
| add heterogeneous distillation loss L_Dist (ablation) | BuIQA framework · BI-OQA ablation | SRCC: 0.643 -> 0.818 | Improved |
| add multi-scale attention module (ablation) | BuIQA framework · BI-OQA ablation | SRCC: 0.470 -> 0.818 | Improved |
| add multi-scale features in task-aware feature extraction (ablation) | BuIQA framework · BI-OQA ablation | SRCC: 0.773 -> 0.818 | Improved |
| use proposed framework instead of strongest compared approach | EBSR super-resolution scores · BI-OQA EBSR (SR) R0 | SRCC: at least 0.343 | Improved |
| use proposed framework instead of strongest compared approach | EBSR super-resolution scores · BI-OQA EBSR (SR) R0.1 | SRCC: 0.561 -> 0.718 | Improved |
| relax tie threshold from R0 to R0.1 | Ours · BI-OQA EBSR (SR) | SRCC: 0.486 -> 0.718 | Improved |
| use proposed framework instead of strongest compared approach | subjective frame selection · BI-SQA Photo Triage | pairwise accuracy: 0.680 -> 0.706 | Improved |
| use proposed framework instead of strongest compared approach | subjective frame selection · BI-SQA SPAQ | pairwise accuracy: 0.566 -> 0.582 | Improved |
| use video quality assessment model KVQ instead of VGG-16 baseline | subjective frame selection · BI-SQA Photo Triage | pairwise accuracy: 0.631 -> 0.533 | Hurt |
Closest papers by meaning
- QMambaBSR: Burst Image Super-Resolution with Query State Space Model (CVPR 2025 · similarity 0.86)
- Burst Image Restoration and Enhancement (CVPR 2022 · similarity 0.85)
- Dynamic Exposure Burst Image Restoration (CVPR 2026 · similarity 0.84)
- Self-Supervised Burst Super-Resolution (ICCV 2023 · similarity 0.84)
- Deep Burst Super-Resolution (CVPR 2021 · similarity 0.84)
- Modular Blind Video Quality Assessment (CVPR 2024 · similarity 0.81)
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.
