Research map / 3D vision / Face and shape
FitMe: Deep Photorealistic 3D Morphable Model Avatars
Alexandros Lattas, Stylianos Moschoglou, Stylianos Ploumpis, Baris Gecer, Jiankang Deng, Stefanos Zafeiriou
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 during GAN inversion (ablation) | FitMe · Single-image reconstruction | identity and visual similarity | Improved |
| Add perceptual loss during GAN inversion (ablation) | FitMe · Single-image reconstruction | visual similarity | Improved |
| Add photometric loss during GAN inversion (ablation) | FitMe · Single-image reconstruction | visual similarity | Improved |
| Add W regularization during GAN inversion (ablation) | FitMe · Single-image reconstruction | albedo without scene illumination | Improved |
| Add landmark and shape/expression regularization losses during GAN inversion (ablation) | FitMe · Single-image reconstruction | shape fitting | Improved |
| Add photometric loss during GAN tuning (ablation) | FitMe · Single-image reconstruction | likeness to input image | Improved |
| Add LPIPS loss during GAN tuning (ablation) | FitMe · Single-image reconstruction | likeness to input image | Improved |
| Add flip and chromaticity losses during GAN tuning (ablation) | FitMe · Single-image reconstruction | albedo without scene illumination | Improved |
| Tune the generator after GAN inversion (ablation) | FitMe · Single-image reconstruction | identity similarity | Improved |
| Optimize W rather than W+ (ablation) | FitMe · Single-image reconstruction | reflectance semantics | Improved |
| Use FitMe's photorealistic facial shading instead of the Phong shader (ablation) | FitMe · Single-image reconstruction | photorealistic reflectance reconstruction | Improved |
| Optimize W rather than z through the mapping network (ablation) | FitMe · Single-image reconstruction | identity similarity | Improved |
Later papers that compared with this method
1 later accepted paper reports FitMe as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- MoSAR: Monocular Semi-Supervised Model for Avatar Reconstruction using Differentiable Shading (CVPR 2024 · better on 1 of 1 shared result)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.
- GANFit — GANFIT: Generative Adversarial Network Fitting for High Fidelity 3D Face Reconstruction (CVPR 2019) · better on 0 of 6 shared results
- Fast-GANFit — Fast-GANFIT: Generative Adversarial Network for High Fidelity 3D Face Reconstruction (TPAMI 2021) · better on 3 of 3 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
- AvatarMe++: Facial Shape and BRDF Inference With Photorealistic Rendering-Aware GANs (TPAMI 2021 · similarity 0.90)
- AvatarMe: Realistically Renderable 3D Facial Reconstruction "In-the-Wild" (CVPR 2020 · similarity 0.90)
- RGBAvatar: Reduced Gaussian Blendshapes for Online Modeling of Head Avatars (CVPR 2025 · similarity 0.86)
- LeGO: Leveraging a Surface Deformation Network for Animatable Stylized Face Generation with One Example (CVPR 2024 · similarity 0.86)
- MoSAR: Monocular Semi-Supervised Model for Avatar Reconstruction using Differentiable Shading (CVPR 2024 · similarity 0.86)
- Morphable Diffusion: 3D-Consistent Diffusion for Single-image Avatar Creation (CVPR 2024 · similarity 0.86)
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.
