Research map / Image generation / Editing and style transfer
Deep Saliency Prior for Reducing Visual Distraction
Kfir Aberman, Junfeng He, Yossi Gandelsman, Inbar Mosseri, David E. Jacobs, Kai Kohlhoff, Yael Pritch, Michael Rubinstein
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 saliency-guided editing instead of Look-here! | Distracting regions in images · Perceptual study, predicted saliency | saliency reduction: 25.8% vs 43.1% (Recolor), 92.9% (Warp), and 53.3% (ConvNet) | Improved |
| Use saliency-guided warping rather than Look-here! | Distracting regions in images · User preference, Warp comparison | user preference: 9.4% vs 84.4 | Improved |
| Use saliency-guided recoloring rather than Look-here! | Distracting regions in images · User preference, Recolor comparison | user preference: 31.3% vs 62.5% | Improved |
| Use the saliency-guided ConvNet effect rather than Look-here! | Distracting regions in images · User preference, ConvNet comparison | user preference: 18.8% vs 75% | Improved |
| Apply saliency-guided editing with the tested operators | Marked regions in images · User gaze study, 31 images | gaze saliency within the mask: t=-4.5; p=6×10^{-5} | Improved |
| Apply saliency-guided editing with the tested operators | Marked regions in images · User gaze study, 31 images | consecutive gaze duration within the mask: t=-3.3; p=2.2×10^{-5} | Improved |
| Apply saliency-guided editing with the tested operators | Marked regions in images · User gaze study, 31 images | first gaze time: t=3.5; p=1.2×10^{-3} | Improved |
| Use saliency-guided warping instead of recoloring, ConvNet, or GAN | Marked regions in the real-gaze study · Perceptual study, real gaze | gaze saliency reduction: 43.1% (Recolor), 92.9% (Warp), 53.3% (ConvNet), 34.8% (GAN) | Mixed |
| Use the proposed edits instead of leaving the image unedited | Images in the realism study · User realism study | images marked realistic: 85% -> 78% | Hurt |
Closest papers by meaning
- Realistic Saliency Guided Image Enhancement (CVPR 2023 · similarity 0.88)
- Understanding and Visualizing Deep Visual Saliency Models (CVPR 2019 · similarity 0.87)
- Learning Gaze Transitions From Depth to Improve Video Saliency Estimation (ICCV 2017 · similarity 0.87)
- Saliency Prediction in the Deep Learning Era: Successes and Limitations (TPAMI 2019 · similarity 0.87)
- Inferring Attention Shifts for Salient Instance Ranking (IJCV 2023 · similarity 0.87)
- Correcting Visual Blur Induced by Attention Distraction to Reduce Hallucinations: Algorithm and Theory (ICML 2026 · 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.
