Research map / 3D vision / 3D generation
Pose Guided Image Generation from Misaligned Sources via Residual Flow Based Correction
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 residual flow correction (ablation) | Multi-source pose-guided image generation · DeepFashion, K=2 | FID: 10.292 -> 10.135 | Helped |
| Add residual flow correction (ablation) | Multi-source pose-guided image generation · Market-1501, K=2 | FID: 17.701 -> 15.716 | Helped |
| Add residual flow correction (ablation) | Multi-source pose-guided image generation · Market-1501, K=2 | LPIPS: 0.2679 -> 0.2668 | Helped |
| Add residual flow correction (ablation) | Multi-source pose-guided image generation · Market-1501, K=2 | MLPIPS: 0.1483 -> 0.1339 | Helped |
| Add attention maps to weight source regions (ablation) | Multi-source pose-guided image generation · DeepFashion, K=2 | FID: 10.835 -> 10.135 | Helped |
| Add attention maps to weight source regions (ablation) | Multi-source pose-guided image generation · Market-1501, K=2 | FID: 15.820 -> 15.716 | Mixed |
| Add attention maps to weight source regions (ablation) | Multi-source pose-guided image generation · DeepFashion, K=2 | LPIPS: 0.1774 -> 0.1766 | Helped |
| Add occlusion maps for invisible or unreliable regions (ablation) | Multi-source pose-guided image generation · DeepFashion, K=2 | FID: 10.421 -> 10.135 | Helped |
| Add occlusion maps for invisible or unreliable regions (ablation) | Multi-source pose-guided image generation · DeepFashion, K=2 | LPIPS: 0.1830 -> 0.1766 | Helped |
| Add occlusion maps for invisible or unreliable regions (ablation) | Multi-source pose-guided image generation · Market-1501, K=2 | FID: 15.249 -> 15.716 | Hurt |
| Add occlusion maps for invisible or unreliable regions (ablation) | Multi-source pose-guided image generation · Market-1501, K=2 | LPIPS: 0.2689 -> 0.2668 | Helped |
| Add occlusion maps for invisible or unreliable regions (ablation) | Multi-source pose-guided image generation · Market-1501, K=2 | MLPIPS: 0.1349 -> 0.1339 | Helped |
Closest papers by meaning
- Disentangled Pose and Appearance Guidance for Multi-Pose Generation (CVPR 2025 · similarity 0.85)
- IMAGPose: A Unified Conditional Framework for Pose-Guided Person Generation (NeurIPS 2024 · similarity 0.84)
- PoseGen: Learning to Generate 3D Human Pose Dataset with NeRF (AAAI 2024 · similarity 0.84)
- NVComposer: Boosting Generative Novel View Synthesis with Multiple Sparse and Unposed Images (CVPR 2025 · similarity 0.84)
- Can Generative Video Models Help Pose Estimation? (CVPR 2025 · similarity 0.84)
- SceneDesigner: Controllable Multi-Object Image Generation with 9-DoF Pose Manipulation (NeurIPS 2025 · similarity 0.83)
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.