Research map / 3D vision / Face and shape
GDFace: Gated Deformation for Multi-View Face Image Synthesis
Xuemiao Xu, Keke Li, Cheng Xu, Shengfeng He
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 identity-preserving loss (ablation) | GDFace · Multi-PIE Setting 2 | Rank-1 (%) at ±90°: 15.14 -> 90.32 | Improved |
| add adversarial loss (ablation) | GDFace · Multi-PIE Setting 2 | Rank-1 (%) at ±90°: 86.76 -> 90.32 | Improved |
| add 3D shape loss (ablation) | GDFace · Multi-PIE Setting 2 | Rank-1 (%) at ±90°: 88.15 -> 90.32 | Improved |
| add total variation loss (ablation) | GDFace · Multi-PIE Setting 2 | Rank-1 (%) at ±90°: 89.00 -> 90.32 | Improved |
| use gated deformable blocks instead of regular residual blocks (ablation) | GDFace · Multi-PIE Setting 2 | Rank-1 (%) at ±90°: 87.43 -> 90.32 | Improved |
| add soft-gating mechanism (ablation) | GDFace · Multi-PIE Setting 2 | Rank-1 (%) at ±90°: 89.24 -> 90.32 | Mixed |
| add soft-gating mechanism (ablation) | GDFace · Multi-PIE Setting 2 | Rank-1 (%) at ±45°: 99.58 -> 99.68 | Improved |
| GDFace vs prior best at large pose | Multi-PIE Setting 1 · Multi-PIE Setting 1 | Rank-1 (%) at ±90°: 77.10 -> 87.93 | Improved |
| GDFace vs Light CNN-29 on CFP | CFP · CFP Frontal-Profile | AUC (%): 97.77 -> 96.59 | Hurt |
Closest papers by meaning
- DINet: Deformation Inpainting Network for Realistic Face Visually Dubbing on High Resolution Video (AAAI 2023 · similarity 0.86)
- Face2Faceρ: Real-Time High-Resolution One-Shot Face Reenactment (ECCV 2022 · similarity 0.86)
- G-NeRF: Geometry-enhanced Novel View Synthesis from Single-View Images (CVPR 2024 · similarity 0.85)
- Beyond Face Rotation: Global and Local Perception GAN for Photorealistic and Identity Preserving Frontal View Synthesis (ICCV 2017 · similarity 0.84)
- GM-NeRF: Learning Generalizable Model-Based Neural Radiance Fields From Multi-View Images (CVPR 2023 · similarity 0.84)
- Real-time Free-view Human Rendering from Sparse-view RGB Videos using Double Unprojected Textures (CVPR 2025 · similarity 0.84)
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.
