Research map / Image generation / Autoregressive and latent generation
Image Inpainting via Conditional Texture and Structure Dual Generation
Xiefan Guo, Hongyu Yang, Di Huang
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 |
|---|---|---|---|
| add structure priors via a structure stream (ablation) | Texture-structure dual generation · Paris StreetView (mask 40-60%) | LPIPS: 0.251 -> 0.226 | Improved |
| add structure priors via a structure stream (ablation) | Texture-structure dual generation · Paris StreetView (mask 40-60%) | PSNR: 22.22 -> 22.89 | Improved |
| use two-stream dual generation instead of multi-task single-stream (ablation) | Texture-structure dual generation · Paris StreetView (mask 40-60%) | LPIPS: 0.245 -> 0.226 | Improved |
| use two-stream dual generation instead of multi-task single-stream (ablation) | Texture-structure dual generation · Paris StreetView (mask 40-60%) | PSNR: 22.59 -> 22.89 | Improved |
| add Bi-GFF instead of concat+conv fusion (ablation) | Texture-structure dual generation · Paris StreetView (mask 40-60%) | LPIPS: 0.236 -> 0.226 | Improved |
| add Bi-GFF instead of concat+conv fusion (ablation) | Texture-structure dual generation · Paris StreetView (mask 40-60%) | SSIM: 0.567 -> 0.573 | Improved |
| add CFA module (ablation) | Texture-structure dual generation · Paris StreetView (mask 40-60%) | LPIPS: 0.243 -> 0.226 | Improved |
| add CFA module (ablation) | Texture-structure dual generation · Paris StreetView (mask 40-60%) | PSNR: 22.64 -> 22.89 | Improved |
| use multi-scale CFA instead of original contextual attention (ablation) | Texture-structure dual generation · Paris StreetView (mask 40-60%) | LPIPS: 0.240 -> 0.226 | Improved |
| use multi-scale CFA instead of original contextual attention (ablation) | Texture-structure dual generation · Paris StreetView (mask 40-60%) | SSIM: 0.566 -> 0.573 | Improved |
| use dual-generation model instead of RFR | Texture-structure dual generation · Places2 (mask 40-60%) | LPIPS: 0.239 -> 0.227 | Improved |
| use dual-generation model instead of MED (shared generator) | Texture-structure dual generation · Places2 (mask 40-60%) | LPIPS: 0.248 -> 0.227 | Improved |
Closest papers by meaning
- StructureFlow: Image Inpainting via Structure-Aware Appearance Flow (ICCV 2019 · similarity 0.90)
- Contextual-based Image Inpainting: Infer, Match, and Translate (ECCV 2018 · similarity 0.89)
- Generative Image Inpainting With Contextual Attention (CVPR 2018 · similarity 0.89)
- Generating Diverse Structure for Image Inpainting With Hierarchical VQ-VAE (CVPR 2021 · similarity 0.89)
- From Inpainting to Layer Decomposition: Repurposing Generative Inpainting Models for Image Layer Decomposition (CVPR 2026 · similarity 0.88)
- SyFormer: Structure-Guided Synergism Transformer for Large-Portion Image Inpainting (AAAI 2024 · similarity 0.87)
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.
