Research map / Image generation / Editing and style transfer
Structure-aware Person Image Generation with Pose Decomposition and Semantic Correlation
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 |
|---|---|---|---|
| Add part-based flow decomposition instead of predicting one whole-body flow (ablation) | Structure-aware flow method · DeepFashion | FID: 13.736 -> 8.755 | Helped |
| Add pyramid non-local block for long-range part correlations (ablation) | Structure-aware flow method · DeepFashion | FID: 9.302 -> 8.755 | Helped |
| Add pyramid non-local block for long-range part correlations (ablation) | Structure-aware flow method · DeepFashion | SSIM: 0.728 -> 0.726 | Hurt |
| Add hybrid dilated convolution block for local part correlations (ablation) | Structure-aware flow method · DeepFashion | LPIPS: 0.1829 -> 0.1815 | Helped |
| Add hybrid dilated convolution block for local part correlations (ablation) | Structure-aware flow method · DeepFashion | SSIM: 0.729 -> 0.726 | Hurt |
| Use structure-aware flow generation and semantic-correlation modules rather than the strongest listed baseline | Person image generation · Market-1501 | LPIPS: 0.2817 -> 0.2796 | Helped |
| Use structure-aware flow generation and semantic-correlation modules rather than the strongest listed baseline | Person image generation · DeepFashion | LPIPS: 0.2330 -> 0.1815 | Helped |
| Use structure-aware flow generation and semantic-correlation modules rather than the strongest listed baseline | Person image generation · DeepFashion | FID: 7.629 -> 8.755 | Hurt |
Closest papers by meaning
- Unsupervised Person Image Generation With Semantic Parsing Transformation (CVPR 2019 · similarity 0.90)
- Pose Guided Person Image Generation (NeurIPS 2017 · similarity 0.89)
- IMAGPose: A Unified Conditional Framework for Pose-Guided Person Generation (NeurIPS 2024 · similarity 0.89)
- Disentangled Pose and Appearance Guidance for Multi-Pose Generation (CVPR 2025 · similarity 0.86)
- Coarse-to-Fine Latent Diffusion for Pose-Guided Person Image Synthesis (CVPR 2024 · similarity 0.86)
- Learning Flow Fields in Attention for Controllable Person Image Generation (CVPR 2025 · similarity 0.86)
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.