Research map / Image generation / Editing and style transfer
Fashion Editing With Adversarial Parsing Learning
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 FE-GAN instead of Edge-connect | fashion image editing · DeepFashion | PSNR: 26.236 -> 29.552 | Helped |
| use FE-GAN instead of Edge-connect | fashion image editing · MPV | PSNR: 27.557 -> 30.602 | Helped |
| use FE-GAN instead of Edge-connect | fashion image editing · FashionE | PSNR: 29.154 -> 30.974 | Helped |
| add multi-scale attention normalization (ablation) | FE-GAN · FashionE | PSNR: 29.185 -> 30.035 | Helped |
| add multi-scale attention normalization (ablation) | FE-GAN · FashionE | FID: 5.191 -> 4.092 | Helped |
| add the free-form parsing network (ablation) | FE-GAN · FashionE | PSNR: 29.109 -> 30.035 | Helped |
| add the free-form parsing network (ablation) | FE-GAN · FashionE | FID: 5.355 -> 4.092 | Helped |
| add mask loss (ablation) | FE-GAN · FashionE | PSNR: 28.813 -> 30.035 | Helped |
| add foreground loss (ablation) | FE-GAN · FashionE | PSNR: 29.848 -> 30.035 | Helped |
Closest papers by meaning
- Editing in Style: Uncovering the Local Semantics of GANs (CVPR 2020 · similarity 0.88)
- Exploiting Spatial Dimensions of Latent in GAN for Real-Time Image Editing (CVPR 2021 · similarity 0.87)
- EditGAN: High-Precision Semantic Image Editing (NeurIPS 2021 · similarity 0.87)
- ManiGAN: Text-Guided Image Manipulation (CVPR 2020 · similarity 0.87)
- E$^2$GAN: Efficient Training of Efficient GANs for Image-to-Image Translation (ICML 2024 · similarity 0.87)
- Learning to Manipulate Artistic Images (AAAI 2024 · 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.