Research map / Image generation / Editing and style transfer
PCGAN: Partition-Controlled Human Image Generation
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 |
|---|---|---|---|
| Use PCGAN instead of Def. GAN | Human image generation · Market-1501 | IS: 3.185 -> 3.657 | Helped |
| Use PCGAN instead of Def. GAN | Human image generation · Market-1501 | mask-IS: 3.502 -> 3.614 | Helped |
| Use PCGAN instead of Def. GAN | Human image generation · Market-1501 | FID: 45.958 -> 20.355 | Helped |
| Use PCGAN instead of Def. GAN | Human image generation · DeepFashion | IS: 3.439 -> 3.536 | Helped |
| Use PCGAN instead of Def. GAN | Human image generation · DeepFashion | FID: 19.200 -> 29.684 | Hurt |
| Add region-mask feature processing to the Deformable GAN baseline (ablation) | Human image generation · LIP | IS: 3.383 -> 4.794 | Helped |
| Add region-mask feature processing to the Deformable GAN baseline (ablation) | Human image generation · COCO2017 | IS: 3.576 -> 5.237 | Helped |
| Add region-mask feature processing to the Deformable GAN baseline (ablation) | Human image generation · Market-1501 | IS: 3.185 -> 3.821 | Helped |
| Add region-mask feature processing to the Deformable GAN baseline (ablation) | Human image generation · Fashion | IS: 3.168 -> 3.168 | No clear effect |
| Replace region masks with more accurate Mask-RCNN or ground-truth masks (ablation) | R-Mask · LIP | IS: 4.794 -> 4.957 | Helped |
| Replace region masks with more accurate Mask-RCNN or ground-truth masks (ablation) | R-Mask · COCO2017 | IS: 5.237 -> 5.448 | Helped |
| Replace region masks with more accurate Mask-RCNN masks (ablation) | R-Mask · Market-1501 | IS: 3.821 -> 3.657 | Hurt |
Closest papers by meaning
- BodyGAN: General-Purpose Controllable Neural Human Body Generation (CVPR 2022 · similarity 0.88)
- Deformable GANs for Pose-Based Human Image Generation (CVPR 2018 · similarity 0.86)
- Pose Guided Person Image Generation (NeurIPS 2017 · similarity 0.85)
- RealisHuman: A Two-Stage Approach for Refining Malformed Human Parts in Generated Images (AAAI 2025 · similarity 0.84)
- IMAGPose: A Unified Conditional Framework for Pose-Guided Person Generation (NeurIPS 2024 · similarity 0.84)
- CGS-GAN: 3D Consistent Gaussian Splatting GANs for High Resolution Human Head Synthesis (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.