Research map / Image generation / Editing and style transfer
Exploring Dual-Task Correlation for Pose Guided Person Image Generation
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 DPTN instead of the strongest listed baseline | Pose-guided person image generation · DeepFashion | PSNR: 18.5867 -> 19.1492 | Helped |
| Use DPTN instead of the strongest listed baseline | Pose-guided person image generation · Market1501 | SSIM: 0.3139 -> 0.2854 | Hurt |
| Use DPTN instead of the strongest listed baseline | Pose-guided person image generation · Market1501 | PSNR: 14.4894 -> 14.5207 | Helped |
| Use DPTN instead of the strongest listed baseline | Pose-guided person image generation · Market1501 | LPIPS: 0.2777 -> 0.2711 | Helped |
| Add source-to-source learning (ablation) | DPTN · DeepFashion | PSNR: 18.8134 -> 19.1492 | Helped |
| Add the Pose Transformer Module (ablation) | DPTN · DeepFashion | LPIPS: 0.2195 -> 0.1957 | Helped |
| Add Context Augment Blocks (ablation) | DPTN Pose Transformer Module · DeepFashion | FID: 12.0932 -> 11.4664 | Helped |
| Add source texture encoder En_s (ablation) | DPTN Pose Transformer Module · DeepFashion | LPIPS: 0.1976 -> 0.1957 | Helped |
| Add source-to-source learning (ablation) | Basic network · Source-to-source task | PSNR: 19.1855 -> 23.7606 | Helped |
| Add source-to-source learning (ablation) | Basic network · Source-to-source task | LPIPS: 0.1962 -> 0.1468 | Helped |
Closest papers by meaning
- IMAGPose: A Unified Conditional Framework for Pose-Guided Person Generation (NeurIPS 2024 · similarity 0.87)
- Coarse-to-Fine Latent Diffusion for Pose-Guided Person Image Synthesis (CVPR 2024 · similarity 0.85)
- Advancing Pose-Guided Image Synthesis with Progressive Conditional Diffusion Models (ICLR 2024 · similarity 0.85)
- GRPose: Learning Graph Relations for Human Image Generation with Pose Priors (AAAI 2025 · similarity 0.85)
- Disentangled Pose and Appearance Guidance for Multi-Pose Generation (CVPR 2025 · similarity 0.84)
- Stable-Pose: Leveraging Transformers for Pose-Guided Text-to-Image Generation (NeurIPS 2024 · similarity 0.84)
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.