Research map / 3D vision / Face and shape
FaceScape: 3D Facial Dataset and Benchmark for Single-View 3D Face Reconstruction
Hao Zhu, Haotian Yang, Longwei Guo, Yidi Zhang, Yanru Wang, Mingkai Huang, Menghua Wu, Qiu Shen, Ruigang Yang, Xun Cao
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 dynamic detail synthesis (per-expression displacement maps) instead of one source displacement map (ablation) | SVFR rigged model · FaceScape test | wrinkle fidelity | Improved |
| add deforming map as displacement network input instead of one-hot expression code (ablation) | SVFR rigged model · FaceScape test | expression detail | Improved |
| SVFR with bilinear model versus DFDN | SVFR · FaceScape test (source expression) | mean point-to-surface error: 2.19 -> 1.22 | Improved |
| evaluate all 20 expressions instead of source expression only | SVFR · FaceScape test | mean point-to-surface error: 1.22 -> 1.39 | Hurt |
| side view 60-90 deg versus frontal 0-5 deg | DECA · FS-Wild | Chamfer distance: 2.92 -> 4.81 | Hurt |
| side view 60-90 deg versus frontal 0-5 deg | FaceScape(Opti.) · FS-Wild | Chamfer distance: 1.97 -> 7.11 | Hurt |
| side view 60-90 deg versus frontal 0-5 deg | MGCNet · FS-Wild | Chamfer distance: 3.11 -> 4.20 | Hurt |
| short focal (300) versus long focal (1200) | DECA · FS-Lab | Chamfer distance: 4.07 -> 5.81 | Hurt |
| train with multi-view images (MGCNet) versus frontal-focused methods on side views | MGCNet · FS-Wild 60-90 deg | Chamfer distance: 7.11 -> 4.20 | Improved |
Closest papers by meaning
- FaceScape: A Large-Scale High Quality 3D Face Dataset and Detailed Riggable 3D Face Prediction (CVPR 2020 · similarity 0.97)
- How Far Are We From Solving the 2D & 3D Face Alignment Problem? (And a Dataset of 230,000 3D Facial Landmarks) (ICCV 2017 · similarity 0.89)
- Learning Complete 3D Morphable Face Models From Images and Videos (CVPR 2021 · similarity 0.89)
- Regressing Robust and Discriminative 3D Morphable Models With a Very Deep Neural Network (CVPR 2017 · similarity 0.89)
- Pixel3DMM: Versatile Screen-Space Priors for Single-Image 3D Face Reconstruction (ICLR 2026 · similarity 0.89)
- Large Pose 3D Face Reconstruction From a Single Image via Direct Volumetric CNN Regression (ICCV 2017 · 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.
