Research map / 3D vision / Face and shape
A Generative Model for Depth-Based Robust 3D Facial Pose Tracking
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 |
|---|---|---|---|
| Use the probabilistic generative face model and ray visibility score instead of depth-based baselines | 3D facial pose tracking · Biwi | Yaw error (°): 8.9 -> 2.3 | Helped |
| Use the probabilistic generative face model and ray visibility score instead of depth-based baselines | 3D facial pose tracking · Biwi | Pitch error (°): 8.5 -> 2.0 | Helped |
| Use the probabilistic generative face model and ray visibility score instead of depth-based baselines | 3D facial pose tracking · Biwi | Roll error (°): 7.9 -> 1.9 | Helped |
| Use the probabilistic generative face model and ray visibility score instead of depth-based baselines | 3D facial pose tracking · Biwi | Translation error (mm): 14.0 -> 6.9; 5.9 | Mixed |
| Use the probabilistic generative face model and ray visibility score instead of random forests | 3D facial pose tracking · ICT-3DHP | Yaw error (°): 7.2 -> 3.4 | Helped |
| Use the probabilistic generative face model and ray visibility score instead of random forests | 3D facial pose tracking · ICT-3DHP | Pitch error (°): 9.4 -> 3.2 | Helped |
| Use the probabilistic generative face model and ray visibility score instead of random forests | 3D facial pose tracking · ICT-3DHP | Roll error (°): 7.5 -> 3.3 | Helped |
| Replace ICP registration with ray visibility scoring (ablation) | Generic face model pose estimation · Qualitative occlusion and pose examples | Pose alignment under occlusion | Helped |
| Use the ray visibility score instead of maximizing the face-model likelihood (ablation) | Generic face model pose estimation · Qualitative occlusion and pose examples | Pose alignment under occlusion | Helped |
| Add particle swarm optimization to ray visibility score pose estimation (ablation) | Generic face model pose estimation · Qualitative large-rotation and occlusion examples | Pose alignment | Helped |
| Adapt the generic face model online to the user's identity (ablation) | 3D facial pose tracking · Biwi and ICT-3DHP | Rotation and translation errors | Helped |
Closest papers by meaning
- Unsupervised Depth Estimation, 3D Face Rotation and Replacement (NeurIPS 2018 · similarity 0.87)
- 3D Face Tracking from 2D Video through Iterative Dense UV to Image Flow (CVPR 2024 · similarity 0.86)
- Prior-free 3D Object Tracking (CVPR 2025 · similarity 0.85)
- DiffPortrait3D: Controllable Diffusion for Zero-Shot Portrait View Synthesis (CVPR 2024 · similarity 0.84)
- DPHMs: Diffusion Parametric Head Models for Depth-based Tracking (CVPR 2024 · similarity 0.83)
- KPA-Tracker: Towards Robust and Real-Time Category-Level Articulated Object 6D Pose Tracking (AAAI 2024 · similarity 0.83)
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.