Research map / 3D vision / Face and shape
Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network
Yao Feng, Fan Wu, Xiaohu Shao, Yanfeng Wang, Xi Zhou
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 weight mask (16:4:3:0 ratio) to the position map loss (ablation) | PRN · AFLW2000-3D sparse and dense alignment CED | NME | Improved |
| weight landmarks and central face more (ratio 16:4:3:0 instead of 1:1:1:0) (ablation) | PRN · AFLW2000-3D 68 landmarks | NME | Improved |
| regress UV position map with PRN instead of volumetric regression (VRN-Guided) | 3D face reconstruction · Florence | NME (relative): 28.7% relative higher performance | Improved |
| regress position map directly instead of 3DMM-based dense alignment (3DDFA, DeFA) | dense face alignment · AFLW2000-3D (45K points) | NME: more than 27% | Improved |
| use PRN instead of 3DSTN for sparse alignment | face alignment · AFLW2000-3D mean NME | NME (%): 4.49 -> 3.62 | Improved |
| use PRN instead of a two-stage pipeline for runtime | face alignment and reconstruction · runtime per image | ms: 19.0 -> 9.8 | Improved |
Closest papers by meaning
- Large Pose 3D Face Reconstruction From a Single Image via Direct Volumetric CNN Regression (ICCV 2017 · similarity 0.91)
- How Far Are We From Solving the 2D & 3D Face Alignment Problem? (And a Dataset of 230,000 3D Facial Landmarks) (ICCV 2017 · similarity 0.90)
- Faster Than Real-Time Facial Alignment: A 3D Spatial Transformer Network Approach in Unconstrained Poses (ICCV 2017 · similarity 0.90)
- Unrestricted Facial Geometry Reconstruction Using Image-To-Image Translation (ICCV 2017 · similarity 0.89)
- A Simple, Fast and Highly-Accurate Algorithm to Recover 3D Shape from 2D Landmarks on a Single Image (TPAMI 2017 · similarity 0.89)
- MMFace: A Multi-Metric Regression Network for Unconstrained Face Reconstruction (CVPR 2019 · 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.
