Research map / Image generation / Editing and style transfer
Translate the Facial Regions You Like Using Self-Adaptive Region Translation
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 SART instead of the strongest listed baseline, StarGAN | SART · Morph | Accuracy: 60.88 -> 69.01 | Helped |
| Use SART instead of the strongest listed baseline, FUNIT | SART · Morph | FID: 26.14 -> 23.34 | Helped |
| Use SART instead of the strongest listed baseline, StarGAN | SART · RaFD | Accuracy: 77.28 -> 88.32 | Helped |
| Use SART instead of the strongest listed baseline, SEAN | SART · RaFD | FID: 29.61 -> 27.88 | Helped |
| Use SART instead of the strongest listed baseline, FUNIT | SART · CelebAMask-HQ | Accuracy: 93.30 -> 97.06 | Helped |
| Use SART instead of the strongest listed baseline, FUNIT | SART · CelebAMask-HQ | FID: 35.17 -> 31.06 | Helped |
| Add RIN rather than replacing it with SEAN (ablation) | SART · CelebAMask-HQ | FID: 35.01 -> 31.06 | Helped |
| Add RIN rather than replacing it with SEAN (ablation) | SART · CelebAMask-HQ | Accuracy: 96.85 -> 97.06 | Helped |
| Add region matching loss (ablation) | SART · CelebAMask-HQ | Accuracy: 96.61 -> 97.06 | Helped |
| Add region matching loss (ablation) | SART · CelebAMask-HQ | FID: 33.81 -> 31.06 | Helped |
| Replace RIN with SEAN (ablation) | SART · CelebAMask-HQ | LPIPS: 0.3494 -> 0.3450 | No clear effect |
| Add region matching loss (ablation) | SART · CelebAMask-HQ | LPIPS: 0.3421 -> 0.3450 | No clear effect |
Closest papers by meaning
- StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation (CVPR 2018 · similarity 0.88)
- SEAN: Image Synthesis With Semantic Region-Adaptive Normalization (CVPR 2020 · similarity 0.87)
- TraVeLGAN: Image-To-Image Translation by Transformation Vector Learning (CVPR 2019 · similarity 0.87)
- Encoding in Style: A StyleGAN Encoder for Image-to-Image Translation (CVPR 2021 · similarity 0.86)
- InstaGAN: Instance-aware Image-to-Image Translation (ICLR 2019 · similarity 0.86)
- Rethinking the Paradigm of Content Constraints in Unpaired Image-to-Image Translation (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.