Research map / 3D vision / Face and shape
Extreme 3D Face Reconstruction: Seeing Through Occlusions
Read the paperCheck 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 |
|---|---|---|---|
| Evaluate foundation shapes on occluded rather than unoccluded faces | Tran et al. [51] foundation shape · LFW | Accuracy: 89.91±0.86 -> 87.86±1.35 | Hurt |
| Add occlusions to bump maps | Baseline bump maps · LFW | Accuracy: 92.76±1.22 -> 75.96±1.98 | Hurt |
| Fill occluded bump-map regions using matching reference details | Bump maps with occlusions · LFW | Accuracy: 75.96±1.98 -> 84.06±1.96 | Helped |
| Add gradient terms to the bump-map L1 loss (ablation) | Bump-map estimation network · Bump-map training | Visual noise and surface smoothness | Helped |
Closest papers by meaning
- Generating Diverse 3D Reconstructions From a Single Occluded Face Image (CVPR 2022 · similarity 0.89)
- A Hierarchical Representation Network for Accurate and Detailed Face Reconstruction From In-the-Wild Images (CVPR 2023 · similarity 0.88)
- Photorealistic Facial Texture Inference Using Deep Neural Networks (CVPR 2017 · similarity 0.88)
- Learning Detailed Face Reconstruction From a Single Image (CVPR 2017 · similarity 0.87)
- Towards High-Fidelity 3D Face Reconstruction From In-the-Wild Images Using Graph Convolutional Networks (CVPR 2020 · similarity 0.87)
- OFER: Occluded Face Expression Reconstruction (CVPR 2025 · similarity 0.87)
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.