Research map / Image generation / Editing and style transfer
CCR: Facial Image Editing with Continuity, Consistency and Reversibility
Nan Yang, Xin Luan, Huidi Jia, Zhi Jun Han, Xiaofeng Li, Yandong Tang
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 |
|---|---|---|---|
| add identity loss to encoder training (ablation) | CCR · CelebA-HQ sequential editing Path 1 | EAC: 59.41% -> 54.90% | Hurt |
| add identity loss to encoder training (ablation) | CCR · CelebA-HQ sequential editing Path 2 | EAC: 60.49% -> 57.81% | Hurt |
| add identity loss to encoder training (ablation) | CCR · CelebA-HQ single attribute editing (Glasses) | EAC: 0.9265 -> 0.7231 | Hurt |
| add identity loss to encoder training (ablation) | CCR · CelebA-HQ reversible editing | RAC: 94.97% -> 95.63% | Improved |
| use attention and affine transformation modules together for feature fusion (ablation) | CCR · CelebA-HQ glasses editing (qualitative) | fused feature map quality | Improved |
| replace HiSD with CCR (add multi-domain consistency and reversibility training) | HiSD · CelebA-HQ sequential editing Path 1 | EAC: 52.99% -> 59.41% | Improved |
| replace HiSD with CCR | HiSD · CelebA-HQ reversible editing | RAC: 94.48% -> 94.97% | Improved |
| replace AttGAN with CCR | AttGAN · CelebA-HQ single attribute editing (Glasses) | EAC: 0.9437 -> 0.9265 | Hurt |
| replace STGAN with CCR | STGAN · CelebA-HQ sequential editing | PSNR: 20.5773 -> 20.8347 | Improved |
Closest papers by meaning
- Optimizing ID Consistency in Multimodal Large Models: Facial Restoration via Alignment, Entanglement, and Disentanglement (ICLR 2026 · similarity 0.87)
- CA-Edit: Causality-Aware Condition Adapter for High-Fidelity Local Facial Attribute Editing (AAAI 2025 · similarity 0.87)
- Improving Editability in Image Generation with Layer-wise Memory (CVPR 2025 · similarity 0.85)
- DreamSalon: A Staged Diffusion Framework for Preserving Identity-Context in Editable Face Generation (CVPR 2024 · similarity 0.84)
- CAMILA: Context-Aware Masking for Image Editing with Language Alignment (NeurIPS 2025 · similarity 0.84)
- Pathways on the Image Manifold: Image Editing via Video Generation (CVPR 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.
