Research map / 3D vision / Face and shape
Efficient Global Illumination for Morphable Models
Andreas Schneider, Sandro Schonborn, Lavrenti Frobeen, Bernhard Egger, Thomas Vetter
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 linear self-shadowing (MoMo-PRT) to the local illumination model | Morphable Model rendering · Approximation quality vs full PRT | image RMS difference to full PRT: 3% and higher -> consistently below 1.5% | Improved |
| use linear radiance transfer approximation instead of full PRT | Morphable Model rendering · 50k-vertex face mesh | speedup relative to full PRT: 1 -> 685 | Improved |
| add self-shadowing to model fitting (ablation) | Morphable Model fit · Synthetic face reconstruction (20 images) | shape error (mm): 2.51 -> 2.12 | Improved |
| add self-shadowing to model fitting (ablation) | Morphable Model fit · Synthetic face reconstruction (20 images) | image RMS error: 0.14 -> 0.12 | Improved |
| add self-shadowing to model fitting (ablation) | Morphable Model fit · Synthetic face reconstruction (20 images) | texture RMS error: 0.11 -> 0.11 | No clear effect |
| add self-shadowing to model fitting (ablation) | Morphable Model fit · Synthetic face reconstruction (20 images) | illumination RMS error: 0.14 -> 0.14 | No clear effect |
| use local illumination instead of self-shadowing (speed tradeoff) | Morphable Model rendering · 50k-vertex face mesh | speedup relative to full PRT: 685 -> 1 410 | Mixed |
Closest papers by meaning
- Towards High Fidelity Monocular Face Reconstruction With Rich Reflectance Using Self-Supervised Learning and Ray Tracing (ICCV 2021 · similarity 0.88)
- A Morphable Face Albedo Model (CVPR 2020 · similarity 0.87)
- Learning Complete 3D Morphable Face Models From Images and Videos (CVPR 2021 · similarity 0.86)
- Generative Multiview Relighting for 3D Reconstruction under Extreme Illumination Variation (CVPR 2025 · similarity 0.86)
- RNG: Relightable Neural Gaussians (CVPR 2025 · similarity 0.85)
- InstantSticker: Realistic Decal Blending via Disentangled Object Reconstruction (AAAI 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.
