Research map / 3D vision / Face and shape
Large Pose 3D Face Reconstruction From a Single Image via Direct Volumetric CNN Regression
Aaron S. Jackson, Adrian Bulat, Vasileios Argyriou, Georgios Tzimiropoulos
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 landmark guidance (stack 68 landmark Gaussians with the image) to VRN | VRN · AFLW2000-3D | NME: 0.0676 -> 0.0637 | Improved |
| add landmark guidance to VRN | VRN · BU-4DFE | NME: 0.0600 -> 0.0555 | Improved |
| add landmark guidance to VRN | VRN · Florence | NME: 0.0568 -> 0.0509 | Improved |
| add multitask landmark regression branch to VRN | VRN · AFLW2000-3D | NME: 0.0676 -> 0.0698 | Hurt |
| add multitask landmark regression branch to VRN | VRN · BU-4DFE | NME: 0.0600 -> 0.0625 | Hurt |
| add multitask landmark regression branch to VRN | VRN · Florence | NME: 0.0568 -> 0.0542 | Improved |
| regress a spatially aligned volume instead of a frontalised fixed-orientation volume (ablation) | VRN · 3D face reconstruction (Fig. comparison) | NME | Improved |
| use larger guidance Gaussians (sigma 2 instead of sigma 1) (ablation) | VRN - Guided · 3D face reconstruction | NME | No clear effect |
| increase yaw pose angle (ablation) | VRN - Guided · Florence | NME | Hurt |
| vary facial expression (ablation) | VRN - Guided · BU-4DFE | NME | No clear effect |
Closest papers by meaning
- How Far Are We From Solving the 2D & 3D Face Alignment Problem? (And a Dataset of 230,000 3D Facial Landmarks) (ICCV 2017 · similarity 0.92)
- Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network (ECCV 2018 · similarity 0.91)
- A Simple, Fast and Highly-Accurate Algorithm to Recover 3D Shape from 2D Landmarks on a Single Image (TPAMI 2017 · similarity 0.91)
- Learning Detailed Face Reconstruction From a Single Image (CVPR 2017 · similarity 0.91)
- Face Alignment Across Large Poses: A 3D Solution (CVPR 2016 · similarity 0.90)
- Learning From Millions of 3D Scans for Large-Scale 3D Face Recognition (CVPR 2018 · similarity 0.90)
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.
