Research map / 3D vision / Face and shape
A Face Fairness Framework for 3D Meshes
Sk. Mohammadul Haque, Venu Madhav Govindu
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 face fairness penalty term (ablation) | mesh denoiser · Cube denoising | Mean VPE: 0.0258 -> 0.0129 | Improved |
| add face fairness penalty term (ablation) | mesh denoiser · Cube denoising | Mean NE: 0.5704 -> 0.4633 | Improved |
| use proposed denoiser instead of Sun et al. | mesh denoiser · Cube denoising | Mean VPE: 0.0259 -> 0.0129 | Improved |
| use proposed denoiser instead of guided normal filtering | mesh denoiser · Sphere | Mean VPE: 0.0137 -> 0.0114 | Improved |
| use proposed denoiser instead of guided normal filtering | mesh denoiser · Fandisk | Mean VPE: 0.0123 -> 0.0080 | Improved |
| use proposed denoiser instead of guided normal filtering | mesh denoiser · Bunny face | Mean NE: 15.1061 -> 10.5908 | Improved |
| use proposed denoiser instead of guided normal filtering | mesh denoiser · Sphere | Median NE: 1.7523 -> 2.6380 | Hurt |
| use proposed denoiser instead of guided normal filtering | mesh denoiser · Fandisk | Median NE: 1.7121 -> 1.9092 | Hurt |
| use proposed denoiser instead of guided normal filtering | mesh denoiser · Bunny face | Median NE: 5.1168 -> 5.5742 | Hurt |
| use proposed denoiser instead of bilateral normal filtering | mesh denoiser · Sphere | Mean NE: 9.5190 -> 4.2478 | Improved |
| use mean instead of minimum for beta in the fairness weight (ablation) | fairness penalty · mesh denoising | robustness | Improved |
| add fairness term in mesh-normal fusion (ablation) | mesh refinement · terracotta Buddha, Horse, Jar | visual face quality | Improved |
Closest papers by meaning
- Discovering Geometric Biases in 3D Face Reconstruction: A Curvature-Aware Spectral Framework for Fairness Evaluation (ECCV 2026 · similarity 0.88)
- Generating Diverse 3D Reconstructions From a Single Occluded Face Image (CVPR 2022 · similarity 0.85)
- ReDA:Reinforced Differentiable Attribute for 3D Face Reconstruction (CVPR 2020 · similarity 0.84)
- Pixel3DMM: Versatile Screen-Space Priors for Single-Image 3D Face Reconstruction (ICLR 2026 · similarity 0.84)
- Generating 3D Faces using Convolutional Mesh Autoencoders (ECCV 2018 · similarity 0.84)
- Blind Face Restoration under Extreme Conditions: Leveraging 3D-2D Prior Fusion for Superior Structural and Texture Recovery (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.
