Research map / 3D vision / Face and shape
Unsupervised Depth Estimation, 3D Face Rotation and Replacement
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 a pseudoinverse-based affine solution in the loss and backpropagate through it (ablation) | DepthNet · VGG paired-face validation pairs | MSE: 0.568 -> 0.357 | Helped |
| Add Siamese CNN image features (ablation) | DepthNet with separate depth and geometry · VGG paired-face validation pairs | MSE: 0.568 -> 0.539 | Helped |
| Add Siamese CNN image features (ablation) | DepthNet with pseudoinverse · VGG paired-face validation pairs | MSE: 0.357 -> 0.349 | Helped |
| Add adversarial supervision on depth using ground-truth depth labels (ablation) | DepthNet · 3DFAW test faces | DepthCorr, left pose: 27.36 -> 59.69 | Helped |
| Add adversarial supervision on depth using ground-truth depth labels (ablation) | DepthNet · 3DFAW test faces | MSE (× 10^-5): 7.65 ± 6.97 -> 8.74 ± 6.24 | Hurt |
| Predict depth without depth labels | DepthNet · 3DFAW test faces | MSE (× 10^-5): 8.86 ± 6.55 -> 7.65 ± 6.97 | Helped |
Closest papers by meaning
- Unsupervised Training for 3D Morphable Model Regression (CVPR 2018 · similarity 0.90)
- Deep 3D Portrait From a Single Image (CVPR 2020 · similarity 0.90)
- Regressing Robust and Discriminative 3D Morphable Models With a Very Deep Neural Network (CVPR 2017 · similarity 0.89)
- InverseFaceNet: Deep Monocular Inverse Face Rendering (CVPR 2018 · similarity 0.88)
- GANFIT: Generative Adversarial Network Fitting for High Fidelity 3D Face Reconstruction (CVPR 2019 · similarity 0.88)
- In-N-Out: Faithful 3D GAN Inversion with Volumetric Decomposition for Face Editing (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.