Research map / 3D vision / Face and shape
JNR: Joint-based Neural Rig Representation for Compact 3D Face Modeling
Noranart Vesdapunt, Mitch Rundle, HsiangTao Wu, Baoyuan Wang
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 |
|---|---|---|---|
| learn linear skinning weights instead of hand-painted (ablation) | joint-based face rig · Known correspondence test set | point-to-point error (mm): 0.41 -> 0.34 | Improved |
| learn neural (per-scan) skinning weights instead of linear (ablation) | joint-based face rig · Known correspondence test set | point-to-point error (mm): 0.34 -> 0.11 | Improved |
| learn neural skinning instead of hand-painted (ablation) | joint-based face rig · BU-3DFE neutral scans | RMS error (mm): 0.375 -> 0.153 | Improved |
| learn linear skinning instead of hand-painted (ablation) | joint-based face rig · BU-3DFE neutral scans | RMS error (mm): 0.375 -> 0.338 | Improved |
| learn neural skinning instead of linear (ablation) | joint-based face rig · BU-3DFE neutral scans | RMS error (mm): 0.338 -> 0.153 | Improved |
| learn neural skinning instead of hand-painted (ablation) | joint-based face rig · BU-3DFE expressive scans | RMS error (mm): 0.432 -> 0.218 | Improved |
| learn linear skinning instead of hand-painted (ablation) | joint-based face rig · BU-3DFE expressive scans | RMS error (mm): 0.432 -> 0.405 | Improved |
| learn neural skinning instead of linear (ablation) | joint-based face rig · BU-3DFE expressive scans | RMS error (mm): 0.405 -> 0.218 | Improved |
| add expression blendshapes to neural skinning model (ablation) | joint-based face rig · BU-3DFE expressive scans | RMS error (mm): 0.239 -> 0.218 | Improved |
| use hand-painted skinning instead of Facewarehouse model | joint-based face rig · BU-3DFE neutral scans | RMS error (mm): 0.437 -> 0.375 | Improved |
Closest papers by meaning
- Generating 3D Faces using Convolutional Mesh Autoencoders (ECCV 2018 · similarity 0.89)
- 3DFaceGAN: Adversarial Nets for 3D Face Representation, Generation, and Translation (IJCV 2020 · similarity 0.89)
- Regressing Robust and Discriminative 3D Morphable Models With a Very Deep Neural Network (CVPR 2017 · similarity 0.88)
- FaceVerse: A Fine-Grained and Detail-Controllable 3D Face Morphable Model From a Hybrid Dataset (CVPR 2022 · similarity 0.88)
- Learning to Regress 3D Face Shape and Expression From an Image Without 3D Supervision (CVPR 2019 · similarity 0.88)
- FaceScape: A Large-Scale High Quality 3D Face Dataset and Detailed Riggable 3D Face Prediction (CVPR 2020 · similarity 0.88)
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.
