Research map / Image generation / Autoregressive and latent generation
Semantic Image Inpainting With Deep Generative Models
Check 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 Semantic Image Inpainting instead of Context Encoder | Semantic image inpainting · CelebA, center mask | PSNR (dB): 21.3 -> 19.4 | Hurt |
| Use Semantic Image Inpainting instead of Context Encoder | Semantic image inpainting · SVHN, center mask | PSNR (dB): 22.3 -> 19.0 | Hurt |
| Use Semantic Image Inpainting instead of Context Encoder | Semantic image inpainting · Cars, center mask | PSNR (dB): 14.1 -> 13.5 | Hurt |
| Use Semantic Image Inpainting instead of Context Encoder | Semantic image inpainting · CelebA, pattern mask | PSNR (dB): 19.2 -> 17.4 | Hurt |
| Use Semantic Image Inpainting instead of Context Encoder | Semantic image inpainting · SVHN, pattern mask | PSNR (dB): 22.3 -> 19.8 | Hurt |
| Use Semantic Image Inpainting instead of Context Encoder | Semantic image inpainting · Cars, pattern mask | PSNR (dB): 14.0 -> 14.1 | Helped |
| Use Semantic Image Inpainting instead of Context Encoder | Semantic image inpainting · CelebA, random mask | PSNR (dB): 20.6 -> 22.8 | Helped |
| Use Semantic Image Inpainting instead of Context Encoder | Semantic image inpainting · SVHN, random mask | PSNR (dB): 24.1 -> 33.0 | Helped |
| Use Semantic Image Inpainting instead of Context Encoder | Semantic image inpainting · Cars, random mask | PSNR (dB): 16.1 -> 18.9 | Helped |
| Use Semantic Image Inpainting instead of Context Encoder | Semantic image inpainting · CelebA, half mask | PSNR (dB): 15.5 -> 13.7 | Hurt |
| Use Semantic Image Inpainting instead of Context Encoder | Semantic image inpainting · SVHN, half mask | PSNR (dB): 19.1 -> 14.6 | Hurt |
| Use Semantic Image Inpainting instead of Context Encoder | Semantic image inpainting · Cars, half mask | PSNR (dB): 12.6 -> 11.1 | Hurt |
Closest papers by meaning
- Generative Image Inpainting With Contextual Attention (CVPR 2018 · similarity 0.91)
- Towards Enhanced Image Inpainting: Mitigating Unwanted Object Insertion and Preserving Color Consistency (CVPR 2025 · similarity 0.88)
- Paint by Inpaint: Learning to Add Image Objects by Removing Them First (CVPR 2025 · similarity 0.87)
- Image Inpainting via Tractable Steering of Diffusion Models (ICLR 2024 · similarity 0.86)
- Don't Look into the Dark: Latent Codes for Pluralistic Image Inpainting (CVPR 2024 · similarity 0.86)
- NeRFiller: Completing Scenes via Generative 3D Inpainting (CVPR 2024 · similarity 0.86)
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.