Research map / Image generation / GANs
Make a Face: Towards Arbitrary High Fidelity Face Manipulation
Shengju Qian, Kwan-Yee Lin, Wayne Wu, Yangxiaokang Liu, Quan Wang, Fumin Shen, Chen Qian, Ran He
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 KL divergence loss term (ablation) | AF-VAE · CelebA | FID: 56.275 -> 36.820 | Improved |
| add KL divergence loss term (ablation) | AF-VAE · CelebA | Inception Score: 1.863 -> 2.152 | Improved |
| add additive Gaussian mixture (focal) prior (ablation) | AF-VAE · CelebA | FID: 62.657 -> 36.820 | Improved |
| add additive Gaussian mixture (focal) prior (ablation) | AF-VAE · CelebA | Inception Score: 1.792 -> 2.152 | Improved |
| add sub-pixel convolution (pixel shuffle) upsampling (ablation) | AF-VAE · CelebA | FID: 71.309 -> 36.820 | Improved |
| add sub-pixel convolution (pixel shuffle) upsampling (ablation) | AF-VAE · CelebA | Inception Score: 1.065 -> 2.152 | Improved |
| add weight normalization in encoder and decoder (ablation) | AF-VAE · CelebA | FID: 65.309 -> 36.820 | Improved |
| add weight normalization in encoder and decoder (ablation) | AF-VAE · CelebA | Inception Score: 1.365 -> 2.152 | Improved |
| use AF-VAE instead of GANimation | AF-VAE · Face expression synthesis comparison | FID: 34.360 -> 25.069 | Improved |
| use AF-VAE instead of GANimation | AF-VAE · Face expression synthesis comparison | Inception Score: 1.112 -> 1.237 | Improved |
| use AF-VAE instead of GANimation | AF-VAE · AMT realism study | Fool Rate (%): 7.0% -> 36.4% | Improved |
| replace deconvolution with sub-pixel convolution (ablation) | AF-VAE · reconstruction entropy | image entropy: 7.6405 -> 7.6794 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- StarGAN — StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation (CVPR 2018) · better on 4 of 4 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- 3D-FM GAN: Towards 3D-Controllable Face Manipulation (ECCV 2022 · similarity 0.86)
- MaskGAN: Towards Diverse and Interactive Facial Image Manipulation (CVPR 2020 · similarity 0.86)
- DeepCoder: Semi-Parametric Variational Autoencoders for Automatic Facial Action Coding (ICCV 2017 · similarity 0.86)
- FaceDNeRF: Semantics-Driven Face Reconstruction, Prompt Editing and Relighting with Diffusion Models (NeurIPS 2023 · similarity 0.86)
- 3D Guided Fine-Grained Face Manipulation (CVPR 2019 · similarity 0.85)
- Face Adapter for Pre-Trained Diffusion Models with Fine-Grained ID and Attribute Control (ECCV 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.
