Research map / 3D vision / Face and shape
Automated 3D Face Reconstruction From Multiple Images Using Quality Measures
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 surface-normal differences to assess reconstruction plausibility instead of image distance | 3DMM face reconstruction quality ranking · Obama, automatic landmarks | mean rank error: 6.92 -> 1.33 | Helped |
| Use surface-normal differences to assess reconstruction plausibility instead of image distance | 3DMM face reconstruction quality ranking · Obama, manual landmarks | mean rank error: 6.83 -> 2.25 | Helped |
| Use surface-normal differences rather than Euclidean distance for quality ranking | 3DMM face reconstruction quality ranking · Obama, automatic landmarks | mean rank error: 5.67 -> 1.33 | Helped |
| Use surface-normal differences rather than Mahalanobis distance for quality ranking | 3DMM face reconstruction quality ranking · Obama, automatic landmarks | mean rank error: 2.25 -> 1.33 | Helped |
| Add a 3DMM-derived spatial weight map to Normal distance (ablation) | Normal distance quality ranking · Obama, automatic landmarks | mean rank error: 1.33 -> 1.33 | No clear effect |
| Add a 3DMM-derived spatial weight map to Normal distance (ablation) | Normal distance quality ranking · Obama, manual landmarks | mean rank error: 2.25 -> 2.17 | No clear effect |
| Use surface-normal differences rather than image distance for quality ranking | 3DMM face reconstruction quality ranking · Lawrence, single image | mean rank error: 7.56 -> 5.44 | Helped |
| Use surface-normal differences rather than image distance for quality ranking | 3DMM face reconstruction quality ranking · Annan, single image | mean rank error: 9.59 -> 4.97 | Helped |
| Use surface-normal differences rather than image distance for quality ranking | 3DMM face reconstruction quality ranking · Watson, single image | mean rank error: 13.15 -> 11.50 | Helped |
| Use surface-normal differences rather than image distance for quality ranking | 3DMM face reconstruction quality ranking · Carell, single image | mean rank error: 8.04 -> 2.61 | Helped |
| Use surface-normal differences rather than image distance for quality ranking | 3DMM face reconstruction quality ranking · Watson, multiple images | mean rank error: 10.80 -> 7.85 | Helped |
| Use surface-normal differences rather than image distance for quality ranking | 3DMM face reconstruction quality ranking · Carell, multiple images | mean rank error: 6.32 -> 4.96 | Helped |
Closest papers by meaning
- Adaptive 3D Face Reconstruction From Unconstrained Photo Collections (CVPR 2016 · similarity 0.86)
- Generating Diverse 3D Reconstructions From a Single Occluded Face Image (CVPR 2022 · similarity 0.86)
- Fast 3D Reconstruction of Faces With Glasses (CVPR 2017 · similarity 0.86)
- Pixel3DMM: Versatile Screen-Space Priors for Single-Image 3D Face Reconstruction (ICLR 2026 · similarity 0.86)
- OFER: Occluded Face Expression Reconstruction (CVPR 2025 · similarity 0.86)
- PSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion and Explicit Remeshing (CVPR 2025 · 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.