Research map / Image generation / Editing and style transfer
Realistic Saliency Guided Image Enhancement
S. Mahdi H. Miangoleh, Zoya Bylinskii, Eric Kee, Eli Shechtman, Yağiz Aksoy
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 |
|---|---|---|---|
| use the realism network instead of adversarial training (ablation) | Realistic Saliency Guided Image Enhancement · Adobe Stock, attenuation | Effectiveness: 5.06 (2.84) -> 6.36 (2.79) | Improved |
| use the realism network instead of adversarial training (ablation) | Realistic Saliency Guided Image Enhancement · Adobe Stock, attenuation | Realism: 7.36 (3.07) -> 6.34 (2.88) | Hurt |
| use realism-selected edit ordering rather than random ordering | Realistic Saliency Guided Image Enhancement · Adobe Stock, amplification | Realism: 8.27 (1.94) -> 8.31 (1.89) | No clear effect |
| use saliency-selected edit ordering rather than random ordering | Realistic Saliency Guided Image Enhancement · Adobe Stock, amplification | Effectiveness: 7.36 (2.21) -> 7.50 (2.08) | No clear effect |
| use the proposed method rather than GazeShift | Realistic Saliency Guided Image Enhancement · Adobe Stock, attenuation | Effectiveness: 4.78 (2.89) -> 6.36 (2.79) | Improved |
| use the proposed method rather than GazeShift | Realistic Saliency Guided Image Enhancement · Adobe Stock, amplification | Realism: 7.07 (2.76) -> 8.27 (1.94) | Improved |
| use the proposed method rather than DeepSal | Realistic Saliency Guided Image Enhancement · Adobe Stock, attenuation | Effectiveness: 4.04 (2.90) -> 6.36 (2.79) | Improved |
| use the proposed method rather than DeepSal | Realistic Saliency Guided Image Enhancement · DeepSal webpage images, attenuation | Realism: 5.82 (3.43) -> 7.41 (2.70) | Improved |
| use the proposed method rather than MEC | Realistic Saliency Guided Image Enhancement · Mechrez dataset, amplification | Realism: 7.31 (2.93) -> 8.88 (1.74) | Improved |
| use the proposed method rather than MEC | Realistic Saliency Guided Image Enhancement · Mechrez dataset, amplification | Effectiveness: 7.06 (2.68) -> 6.24 (2.9) | No clear effect |
| use the proposed method rather than WRS | Realistic Saliency Guided Image Enhancement · Mechrez dataset, amplification | Effectiveness: 5.41 (3.22) -> 6.24 (2.9) | Improved |
| use the proposed method rather than OHR | Realistic Saliency Guided Image Enhancement · Mechrez dataset, amplification | Realism: 5.18 (3.76) -> 8.88 (1.74) | Improved |
Closest papers by meaning
- Deep Saliency Prior for Reducing Visual Distraction (CVPR 2022 · similarity 0.88)
- Data Augmentation via Latent Diffusion for Saliency Prediction (ECCV 2024 · similarity 0.86)
- Enhancing Photorealism Enhancement (TPAMI 2022 · similarity 0.85)
- PS-Diffusion: Photorealistic Subject-Driven Image Editing with Disentangled Control and Attention (CVPR 2025 · similarity 0.84)
- AGLLDiff: Guiding Diffusion Models Towards Unsupervised Training-free Real-world Low-light Image Enhancement (AAAI 2025 · similarity 0.84)
- Removing Reflections from RAW Photos (CVPR 2025 · similarity 0.83)
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.
