Research map / Image generation / GANs
Generative Image Inpainting with Segmentation Confusion Adversarial Training and Contrastive Learning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 SCAT with global adversarial training instead of global adversarial training alone (ablation) | Inpainting model · CelebA, 40%-60% mask ratio | FID: 7.84 -> 7.20 | Helped |
| Add textural contrastive learning after SCAT (ablation) | Inpainting model · CelebA, 40%-60% mask ratio | FID: 7.20 -> 6.52 | Helped |
| Add semantic contrastive learning after SCAT and textural contrastive learning (ablation) | Inpainting model · CelebA, 40%-60% mask ratio | FID: 6.52 -> 6.15 | Helped |
| Use the full framework rather than the global-adversarial baseline (ablation) | Inpainting model · CelebA, 40%-60% mask ratio | PSNR: 23.86 -> 24.49 | Helped |
| Use the full framework rather than the global-adversarial baseline (ablation) | Inpainting model · CelebA, 40%-60% mask ratio | Mean l1 error: 0.0593 -> 0.0548 | Helped |
| Use the full framework rather than the global-adversarial baseline (ablation) | Inpainting model · CelebA, 40%-60% mask ratio | SSIM: 0.822 -> 0.836 | Helped |
| Use the proposed framework rather than the strongest reported baseline | Image inpainting methods · Places2 and CelebA, all reported mask ratios | PSNR | Helped |
Closest papers by meaning
- Generative Image Inpainting With Contextual Attention (CVPR 2018 · similarity 0.87)
- UCTGAN: Diverse Image Inpainting Based on Unsupervised Cross-Space Translation (CVPR 2020 · similarity 0.86)
- Image Inpainting via Iteratively Decoupled Probabilistic Modeling (ICLR 2024 · similarity 0.85)
- Towards Enhanced Image Inpainting: Mitigating Unwanted Object Insertion and Preserving Color Consistency (CVPR 2025 · similarity 0.85)
- AdvPaint: Protecting Images from Inpainting Manipulation via Adversarial Attention Disruption (ICLR 2025 · similarity 0.84)
- TurboFill: Adapting Few-step Text-to-image Model for Fast Image Inpainting (CVPR 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.