Research map / Image generation / Image restoration
Debiased Subjective Assessment of Real-World Image Enhancement
Peibei Cao, Zhangyang Wang, Kede Ma
Check 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 |
|---|---|---|---|
| Use Δ MSE rather than DISTS to select test images (ablation) | Debiased subjective assessment · Single image super-resolution | Global ranking: ESRGAN: -1; RankSRGAN: +1; others: 0 | No clear effect |
| Use Δ SSIM rather than DISTS to select test images (ablation) | Debiased subjective assessment · Single image super-resolution | Global ranking: TSRN: -1; DBPN: +1; others: 0 | No clear effect |
| Reduce the number of selected images to K ≥ 7, using the top-12 ranking as reference (ablation) | Debiased subjective assessment · Dehazing, super-resolution, and low-light enhancement | SRCC with top-12 ranking: SRCC> 0.97 | No clear effect |
| Select images to maximize agreement between subjective ranking and publication year | Debiased subjective assessment · Single image super-resolution | SRCC with publication year: 0.958 | Improved |
| Select images to maximize agreement between subjective ranking and publication year | Debiased subjective assessment · Single image dehazing | SRCC with publication year: 0.167 | Mixed |
| Select images to maximize agreement between subjective ranking and publication year | Debiased subjective assessment · Low-light image enhancement | SRCC with publication year: 0.071 | Mixed |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- RankSRGAN — RankSRGAN: Super Resolution Generative Adversarial Networks With Learning to Rank (TPAMI 2021) · better on 0 of 1 shared result
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
- Toward Generalized Image Quality Assessment: Relaxing the Perfect Reference Quality Assumption (CVPR 2025 · similarity 0.86)
- Enhancing Quality of Compressed Images by Mitigating Enhancement Bias Towards Compression Domain (CVPR 2024 · similarity 0.85)
- Evaluation of Visual Processing Should Be Human-Centered, Not Metric-Centered (NeurIPS 2026 · similarity 0.84)
- Augmenting Perceptual Super-Resolution via Image Quality Predictors (CVPR 2025 · similarity 0.84)
- Distilling Spatially-Heterogeneous Distortion Perception for Blind Image Quality Assessment (CVPR 2025 · similarity 0.84)
- AGLLDiff: Guiding Diffusion Models Towards Unsupervised Training-free Real-world Low-light Image Enhancement (AAAI 2025 · 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.
