Research map / 3D vision / Face and shape
Deep Facial Non-Rigid Multi-View Stereo
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| optimize multi-view appearance consistency with learned features | DFNRMVS · BU3DFE, two views with the same expression | Mean geometric error (mm): 1.74 -> 1.11 | Helped |
| use multi-view NRMVS instead of single-view reconstruction | DFNRMVS · BU3DFE | Mean geometric error (mm): 1.38 -> 1.11 | Helped |
| use multi-view NRMVS instead of single-view reconstruction | DFNRMVS · Bosphorus, two views with different expressions | Mean geometric error (mm): 1.47 -> 1.44 | Helped |
| add views from two to four (ablation) | DFNRMVS · ESRC test split | Mean geometric error (mm): 1.04 -> 1.02 | Helped |
| add views from two to four (ablation) | DFNRMVS · ESRC test split | STD geometric error (mm): 0.33 -> 0.29 | Helped |
| replace adaptive face basis with a generic fixed basis (ablation) | DFNRMVS · BU3DFE, same-expression two-view | STD geometric error (mm): 0.29 -> 0.33 | Hurt |
| replace adaptive face basis with a generic fixed basis (ablation) | DFNRMVS · BU3DFE, same-expression two-view | Mean geometric error (mm): 1.11 -> 1.12 | No clear effect |
| add a second optimization level (ablation) | DFNRMVS · BU3DFE | Mean geometric error (mm): 1.29 -> 1.18 | Helped |
| add a third optimization level (ablation) | DFNRMVS · BU3DFE | Mean geometric error (mm): 1.18 -> 1.11 | Helped |
| add a second optimization level (ablation) | DFNRMVS · BU3DFE | Running time (s): 0.12 -> 0.22 | Hurt |
Closest papers by meaning
- MVF-Net: Multi-View 3D Face Morphable Model Regression (CVPR 2019 · similarity 0.91)
- Detailed Facial Geometry Recovery from Multi-View Images by Learning an Implicit Function (AAAI 2022 · similarity 0.90)
- Regressing Robust and Discriminative 3D Morphable Models With a Very Deep Neural Network (CVPR 2017 · similarity 0.89)
- FML: Face Model Learning From Videos (CVPR 2019 · similarity 0.88)
- Unsupervised Depth Estimation, 3D Face Rotation and Replacement (NeurIPS 2018 · similarity 0.88)
- Lightweight Photometric Stereo for Facial Details Recovery (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.