Research map / Image generation / Editing and style transfer
Neural Face Editing With Intrinsic Image Disentangling
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 |
|---|---|---|---|
| Use the disentangling network instead of least-squares 3DMM estimation | illumination estimation · Multi-PIE | average variance of illumination coefficients: 0.36 -> 0.16 | Helped |
| Use the disentangling network instead of a baseline auto-encoder | face reconstruction and smile editing · CelebA face editing | qualitative reconstruction and edit quality | Helped |
| Traverse the implicit albedo manifold for smile editing (ablation) | implicit face representation · smile editing | qualitative edit quality | Hurt |
| Traverse the implicit normal manifold for eyewear editing (ablation) | implicit face representation · eyeglasses editing | qualitative edit effect | No clear effect |
| Traverse the UV manifold for eyewear editing (ablation) | implicit face representation · eyeglasses editing | qualitative edit specificity | Hurt |
| Traverse all implicit manifolds for eyewear editing (ablation) | implicit face representation · eyeglasses editing | qualitative edit specificity | Hurt |
| Traverse the implicit albedo manifold for eyewear editing (ablation) | implicit face representation · eyeglasses editing | qualitative edit fidelity | Helped |
| Traverse the UV manifold for smile editing (ablation) | implicit face representation · smile editing | qualitative smile expression | Helped |
| Traverse both UV and implicit normal manifolds for smile editing (ablation) | implicit face representation · smile editing | qualitative smile strength | Helped |
Closest papers by meaning
- Mask-Guided Portrait Editing With Conditional GANs (CVPR 2019 · similarity 0.90)
- Interpreting the Latent Space of GANs for Semantic Face Editing (CVPR 2020 · similarity 0.90)
- SDGAN: Disentangling Semantic Manipulation for Facial Attribute Editing (AAAI 2024 · similarity 0.86)
- In-N-Out: Faithful 3D GAN Inversion with Volumetric Decomposition for Face Editing (CVPR 2024 · similarity 0.86)
- StrokeFaceNeRF: Stroke-based Facial Appearance Editing in Neural Radiance Field (CVPR 2024 · similarity 0.86)
- DreamSalon: A Staged Diffusion Framework for Preserving Identity-Context in Editable Face Generation (CVPR 2024 · similarity 0.85)
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.