A curvature-aware spectral framework using the Laplace-Beltrami operator detects demographic biases in 3D face reconstruction that Euclidean metrics miss, validated by a user study showing 73.6% perceptual accuracy.
In: Pro- ceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Discovering Geometric Biases in 3D Face Reconstruction: A Curvature-Aware Spectral Framework for Fairness Evaluation
A curvature-aware spectral framework using the Laplace-Beltrami operator detects demographic biases in 3D face reconstruction that Euclidean metrics miss, validated by a user study showing 73.6% perceptual accuracy.