Research map / Image generation / Editing and style transfer
Self-Supervised Correlation Mining Network for 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 |
|---|---|---|---|
| Add DSE instead of using a global style encoder (ablation) | SCM-Net · DeepFashion | FID: 12.86 -> 12.18 | Helped |
| Add DSE instead of using a global style encoder (ablation) | SCM-Net · DeepFashion | IS: 3.2456 -> 3.632 | Helped |
| Add DSE instead of using a global style encoder (ablation) | SCM-Net · DeepFashion | LPIPS: 0.187 -> 0.182 | Hurt |
| Add Cross Channel Fusion to DSE (ablation) | SCM-Net · DeepFashion | FID: 17.08 -> 12.18 | Helped |
| Add Cross Channel Fusion to DSE (ablation) | SCM-Net · DeepFashion | LPIPS: 0.175 -> 0.182 | Hurt |
| Add BSR Loss (ablation) | SCM-Net · DeepFashion | FID: 12.61 -> 12.18 | Helped |
| Add BSR Loss (ablation) | SCM-Net · DeepFashion | SSIM: 0.755 -> 0.751 | Hurt |
| Add BSR Loss (ablation) | SCM-Net · DeepFashion | IS: 3.441 -> 3.632 | Helped |
| Use SCM-Net rather than PISE | Pose-guided person image generation · DeepFashion | FID: 13.61 -> 12.18 | Helped |
| Use SCM-Net rather than Intr-Flow | Pose-guided person image generation · DeepFashion | SSIM: 0.798 -> 0.751 | Hurt |
| Use SCM-Net rather than PISE | Pose-guided person image generation · DeepFashion | LPIPS: 0.2059 -> 0.2142 | Hurt |
| Use SCM-Net rather than MUST | Pose-guided person image generation · DeepFashion | IS: 3.692 -> 3.632 | Hurt |
Closest papers by meaning
- Structure-aware Person Image Generation with Pose Decomposition and Semantic Correlation (AAAI 2021 · similarity 0.85)
- MUST-GAN: Multi-Level Statistics Transfer for Self-Driven Person Image Generation (CVPR 2021 · similarity 0.84)
- Unsupervised Person Image Generation With Semantic Parsing Transformation (CVPR 2019 · similarity 0.84)
- Learning from Synchronization: Self-Supervised Uncalibrated Multi-View Person Association in Challenging Scenes (CVPR 2025 · similarity 0.82)
- Disentangled Pose and Appearance Guidance for Multi-Pose Generation (CVPR 2025 · similarity 0.82)
- MultiPly: Reconstruction of Multiple People from Monocular Video in the Wild (CVPR 2024 · similarity 0.81)
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.