Research map / 3D vision / Face and shape
DF2Net: A Dense-Fine-Finer Network for Detailed 3D Face Reconstruction
Xiaoxing Zeng, Xiaojiang Peng, Yu Qiao
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 |
|---|---|---|---|
| use Fr-Net with skip connection instead of stacking a second F-Net without skip connection (ablation) | DF2Net · qualitative 3D face detail | visual detail quality | Improved |
| add multi-resolution hypercolumn blocks to Fr-Net (ablation) | DF2Net · qualitative 3D face detail | visual detail quality | Improved |
| add F-Net and Fr-Net stages after D-Net (ablation) | DF2Net · qualitative 3D face detail | visual detail quality | Improved |
| train D-Net on mixed 3DMM and reconstructed-real data instead of 3DMM-only coarse model of Pix2vertex | D-Net · qualitative coarse reconstruction | visual quality | Improved |
| use DF2Net instead of Pix2vertex | DF2Net · BU-3DFE (100 subjects) | mean absolute depth error: 3.51 -> 3.37 | Improved |
Closest papers by meaning
- Learning Detailed Face Reconstruction From a Single Image (CVPR 2017 · similarity 0.89)
- A Hierarchical Representation Network for Accurate and Detailed Face Reconstruction From In-the-Wild Images (CVPR 2023 · similarity 0.89)
- CNN-Based Real-Time Dense Face Reconstruction with Inverse-Rendered Photo-Realistic Face Images (TPAMI 2018 · similarity 0.89)
- Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network (ECCV 2018 · similarity 0.88)
- Towards High-Fidelity 3D Face Reconstruction From In-the-Wild Images Using Graph Convolutional Networks (CVPR 2020 · similarity 0.88)
- D2IM-Net: Learning Detail Disentangled Implicit Fields From Single Images (CVPR 2021 · 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.
