Research map / Image generation / Editing and style transfer
Unsupervised Person Image Generation With Semantic Parsing Transformation
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 |
|---|---|---|---|
| Add semantic parsing guidance instead of generating without semantic maps (ablation) | E2E person image generation · DeepFashion | IS: 3.140 -> 3.441 | Helped |
| Add semantic parsing guidance instead of generating without semantic maps (ablation) | E2E person image generation · Market-1501 | IS: 2.776 -> 3.499 | Helped |
| Train semantic transformation and appearance generation jointly end-to-end rather than independently with predicted maps (ablation) | Person image generation · DeepFashion | IS: 3.201 -> 3.441 | Helped |
| Train semantic transformation and appearance generation jointly end-to-end rather than independently with predicted maps (ablation) | Person image generation · Market-1501 | IS: 3.462 -> 3.499 | Helped |
| Train semantic transformation and appearance generation jointly end-to-end rather than independently with predicted maps (ablation) | Person image generation · Market-1501 | SSIM: 0.180 -> 0.203 | Helped |
| Train semantic transformation and appearance generation jointly rather than using two-stage ground-truth maps (ablation) | Person image generation · DeepFashion | IS: 3.350 -> 3.441 | Helped |
| Train semantic transformation and appearance generation jointly rather than using two-stage ground-truth maps (ablation) | Person image generation · DeepFashion | SSIM: 0.740 -> 0.736 | No clear effect |
| Replace semantic-aware style loss with mask-style loss (ablation) | Appearance generation · Person image generation | visual quality | Hurt |
| Replace semantic-aware style loss with patch-style loss (ablation) | Appearance generation · Person image generation | visual quality | Hurt |
| Remove face adversarial loss (ablation) | Appearance generation · Person image generation | face naturalness | Hurt |
Closest papers by meaning
- Structure-aware Person Image Generation with Pose Decomposition and Semantic Correlation (AAAI 2021 · similarity 0.90)
- Disentangled Pose and Appearance Guidance for Multi-Pose Generation (CVPR 2025 · similarity 0.87)
- Coarse-to-Fine Latent Diffusion for Pose-Guided Person Image Synthesis (CVPR 2024 · similarity 0.86)
- SCULPT: Shape-Conditioned Unpaired Learning of Pose-dependent Clothed and Textured Human Meshes (CVPR 2024 · similarity 0.86)
- FreeCloth: Free-form Generation Enhances Challenging Clothed Human Modeling (CVPR 2025 · similarity 0.85)
- Controllable Human Image Generation with Personalized Multi-Garments (CVPR 2025 · 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.