Research map / Image generation / Editing and style transfer
GroupDiff: Diffusion-based Group Portrait Editing
Yuming Jiang, Nanxuan Zhao, Qing Liu, Krishna Kumar Singh, Shuai Yang, Chen Change Loy, Ziwei Liu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| finetune SD Inpainting on the synthesized group-photo data | SD Inpainting · LV-MHP-v2 val | FID: 24.1276 -> 20.4833 | Improved |
| add skeleton control to finetuned SD Inpainting | Finetuned SD Inpainting · LV-MHP-v2 val | FID: 20.4833 -> 20.3351 | Improved |
| add person-aware attention modules (inter- and intra-person guidance) | Finetuned SD Inpainting with Skeleton · LV-MHP-v2 val | PSNR: 18.5688 -> 19.4569 | Improved |
| use box- and skeleton-based hierarchical masking instead of random masks (ablation) | GroupDiff training data engine · LV-MHP-v2 val | FID: 26.2193 -> 18.1035 | Improved |
| use multi-person boundary masks instead of masking one person (ablation) | GroupDiff training data engine · LV-MHP-v2 val | FID: 22.7869 -> 18.1035 | Improved |
| add inter-person guidance (indicator matrix) (ablation) | GroupDiff · LV-MHP-v2 val | PSNR: 19.2612 -> 19.4569 | Improved |
| add intra-person guidance (pose in keys) (ablation) | GroupDiff · LV-MHP-v2 val | PSNR / SSIM / FID: PSNR 19.4236 -> 19.4569; SSIM 0.8034 -> 0.8033 | Mixed |
Closest papers by meaning
- InstructPix2NeRF: Instructed 3D Portrait Editing from a Single Image (ICLR 2024 · similarity 0.85)
- PAIR Diffusion: A Comprehensive Multimodal Object-Level Image Editor (CVPR 2024 · similarity 0.84)
- ID-Patch: Robust ID Association for Group Photo Personalization (CVPR 2025 · similarity 0.83)
- PS-Diffusion: Photorealistic Subject-Driven Image Editing with Disentangled Control and Attention (CVPR 2025 · similarity 0.83)
- An Item Is Worth a Prompt: Versatile Image Editing with Disentangled Control (AAAI 2025 · similarity 0.83)
- EasyRef: Omni-Generalized Group Image Reference for Diffusion Models via Multimodal LLM (ICML 2025 · similarity 0.82)
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.
