Research map / Image generation / Editing and style transfer
Efficient 3D-Aware Facial Image Editing via Attribute-Specific Prompt Learning
Amandeep Kumar, Muhammad Awais, Sanath Narayan, Hisham Cholakkal, Salman Khan, Rao Muhammad Anwer
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 (L_id, L_idvc) and pose preservation losses to LAE training (ablation) | LAE on GMPI · Curly hair attribute | ArcFace ID score: 0.66 -> 0.72 | Improved |
| add identity and pose preservation losses to LAE training (ablation) | LAE on GMPI · Curly hair attribute | depth error: 0.61 -> 0.54 | Improved |
| add pose preservation losses (L_total) (ablation) | LAE on GMPI · Curly hair attribute | pose error: 0.0004 -> 0.0004 | No clear effect |
| use text-driven LAE with style tokens instead of attribute-classifier-based PREIM3D | 3D-aware face editing · Smile editing | attribute altering (AA): 1.51 -> 1.69 | Improved |
| use LAE instead of PREIM3D | 3D-aware face editing · Makeup editing | attribute dependency (AD, lower better): 0.88 -> 0.89 | No clear effect |
| add LAE editing to GMPI backbone | GMPI · Smile editing | depth error: 0.49 -> 0.51 | No clear effect |
| use LAE style tokens instead of training attribute classifiers for each new attribute | PREIM3D · Training time per new attribute | training time: several hours -> 4 to 8 minutes | Improved |
| perturb keyword of prompt (Orange to (0)range) | LAE · Orange hair prompt robustness | edit success | Hurt |
Closest papers by meaning
- Image-to-Image Translation With Disentangled Latent Vectors for Face Editing (TPAMI 2023 · similarity 0.91)
- Text-conditional Attribute Alignment across Latent Spaces for 3D Controllable Face Image Synthesis (CVPR 2024 · similarity 0.89)
- Reference-Based 3D-Aware Image Editing with Triplanes (CVPR 2025 · similarity 0.89)
- SDGAN: Disentangling Semantic Manipulation for Facial Attribute Editing (AAAI 2024 · similarity 0.88)
- 3D-Aware Face Editing via Warping-Guided Latent Direction Learning (CVPR 2024 · similarity 0.88)
- AttriHuman-3D: Editable 3D Human Avatar Generation with Attribute Decomposition and Indexing (CVPR 2024 · similarity 0.87)
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.
