Research map / Image generation / Editing and style transfer
Structure-Transformed Texture-Enhanced Network for Person Image Synthesis
Munan Xu, Yuanqi Chen, Shan Liu, Thomas H. Li, Ge Li
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 PHF attention module (ablation) | STTEN · DeepFashion | FID: 12.771 -> 9.888 | Improved |
| add PHF attention module (ablation) | STTEN · FashionTryOn | FID: 8.240 -> 6.401 | Improved |
| add PHF attention module (ablation) | STTEN · FashionTryOn | SSIM: 0.757 -> 0.782 | Improved |
| add structure loss (ablation) | STTEN · DeepFashion | FID: 11.296 -> 9.888 | Improved |
| add structure loss (ablation) | STTEN · FashionTryOn | FID: 7.407 -> 6.401 | Improved |
| add structure loss (ablation) | STTEN · DeepFashion | SSIM: 0.771 -> 0.774 | Improved |
| use structure-transformed renderer instead of plain encoder (ablation) | STTEN · DeepFashion | FID: 15.503 -> 9.888 | Improved |
| use structure-transformed renderer instead of plain encoder (ablation) | STTEN · FashionTryOn | FID: 14.004 -> 6.401 | Improved |
| use structure-transformed renderer instead of plain encoder (ablation) | STTEN · FashionTryOn | SSIM: 0.744 -> 0.782 | Improved |
| use cross-modality deformable convolution instead of flow-based warping (ablation) | STTEN · DeepFashion | FID: 11.054 -> 9.888 | Improved |
| use cross-modality deformable convolution instead of flow-based warping (ablation) | STTEN · FashionTryOn | FID: 7.146 -> 6.401 | Improved |
| use cross-modality deformable convolution instead of flow-based warping (ablation) | STTEN · FashionTryOn | SSIM: 0.760 -> 0.782 | Improved |
Closest papers by meaning
- Pose-Guided Human Animation From a Single Image in the Wild (CVPR 2021 · similarity 0.88)
- Towards Multi-Pose Guided Virtual Try-On Network (ICCV 2019 · similarity 0.88)
- Person Image Synthesis via Denoising Diffusion Model (CVPR 2023 · similarity 0.88)
- VITON: An Image-Based Virtual Try-On Network (CVPR 2018 · similarity 0.88)
- Exploring Dual-Task Correlation for Pose Guided Person Image Generation (CVPR 2022 · similarity 0.87)
- PICTURE: PhotorealistIC virtual Try-on from UnconstRained dEsigns (CVPR 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.
