Research map / 3D vision / Face and shape
I M Avatar: Implicit Morphable Head Avatars From Videos
Yufeng Zheng, Victoria Fernández Abrevaya, Marcel C. Bühler, Xu Chen, Michael J. Black, Otmar Hilliges
Check 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 |
|---|---|---|---|
| use pose-independent learned blendshapes and skinning fields with implicit geometry | IMavatar · Synthetic dataset (COMA test sequences) | Normals: 5.901 vs 8.130 | Improved |
| use pose-independent learned blendshapes and skinning fields with implicit geometry | IMavatar · Real videos (test sequences) | Expression: 2.548 vs 2.786 | Improved |
| add FLAME pseudo ground-truth supervision (ablation) | IMavatar · Real videos (test sequences) | Expression: 2.843 -> 2.548 | Improved |
| add FLAME pseudo ground-truth supervision (ablation) | IMavatar · Real videos (test sequences) | SSIM: 0.9615 -> 0.9655 | Improved |
| add FLAME pseudo ground-truth supervision (ablation) | IMavatar · Real videos (test sequences) | L1: 0.04918 -> 0.04878 | Mixed |
| remove FLAME pseudo ground-truth supervision (ablation) | IMavatar trained with TrainData+ · One real-video subject | Expression: 2.876 vs 2.955 | No clear effect |
| add noise 0.1 to fitted 3DMM global, neck, and jaw poses (ablation) | IMavatar · Female 2 (MakeHuman) | RGB L1: 0.023 -> 0.062 | Hurt |
| degrade 100% of foreground masks (ablation) | IMavatar · Female 2 (MakeHuman) | RGB L1: 0.023 -> 0.029 | Hurt |
Later papers that compared with this method
5 later accepted papers report IMavatar as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.
- High-Fidelity 3D Head Avatars Reconstruction through Spatially-Varying Expression Conditioned Neural Radiance Field (AAAI 2024 · better on 4 of 4 shared results)
- MonoNPHM: Dynamic Head Reconstruction from Monocular Videos (CVPR 2024 · better on 3 of 3 shared results)
- Instant Volumetric Head Avatars (CVPR 2023 · better on 5 of 5 shared results)
- PointAvatar: Deformable Point-Based Head Avatars From Videos (CVPR 2023 · better on 4 of 4 shared results)
- OTAvatar: One-Shot Talking Face Avatar With Controllable Tri-Plane Rendering (CVPR 2023 · better on 1 of 1 shared result)
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
- HRAvatar: High-Quality and Relightable Gaussian Head Avatar (CVPR 2025 · similarity 0.90)
- RGBAvatar: Reduced Gaussian Blendshapes for Online Modeling of Head Avatars (CVPR 2025 · similarity 0.90)
- Efficient 3D Implicit Head Avatar with Mesh-anchored Hash Table Blendshapes (CVPR 2024 · similarity 0.89)
- DiffusionAvatars: Deferred Diffusion for High-fidelity 3D Head Avatars (CVPR 2024 · similarity 0.89)
- 3D Gaussian Head Avatars with Expressive Dynamic Appearances by Compact Tensorial Representations (CVPR 2025 · similarity 0.89)
- GPAvatar: High-fidelity Head Avatars by Learning Efficient Gaussian Projections (CVPR 2025 · similarity 0.89)
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.
