“On Fairness in Face Albedo Estimation” by Feng, Bolkart, Tesch, Black and Abrevaya

  • ©Haiwen Feng, Timo Bolkart, Joachim Tesch, Michael J. Black, and Victoria Abrevaya

Conference:


Type:


Entry Number: 04

Title:

    On Fairness in Face Albedo Estimation

Presenter(s)/Author(s):


Abstract:


    Digital avatars will be crucial components for immersive telecommunication, gaming, and the coming metaverse. Unfortunately, current methods for estimating the facial appearance (albedo) are biased to estimate light skin tones. This talk raises awareness of the problem with an analysis of (1) dataset biases and (2) the light/albedo ambiguity. We show how these problems can be ameliorated by recent advances, improving fairness in albedo estimation.

References:


    V. Blanz and T. Vetter. 1999. A morphable model for the synthesis of 3D faces. In SIGGRAPH. 187–194.Google Scholar
    J. Buolamwini and T. Gebru. 2018. Gender Shades: Intersectional Accuracy Disparities in Commercial Gender Classification(Proceedings of Machine Learning Research, Vol. 81). PMLR, 77–91.Google Scholar
    A. Chardon, I. Cretois, and C. Hourseau. 1991. Skin colour typology and suntanning pathways. Int. J. of Cosmetic Science 13, 4 (1991), 191–208.Google ScholarCross Ref
    S. Del Bino and F. Bernerd. 2013. Variations in skin colour and the biological consequences of ultraviolet radiation exposure. BJD 169(2013), 33–40.Google ScholarCross Ref
    B. Egger, W. A. P. Smith, A. Tewari, S. Wuhrer, M. Zollhöfer, T. Beeler, F. Bernard, T. Bolkart, A. Kortylewski, S. Romdhani, C. Theobalt, V. Blanz, and T. Vetter. 2020. 3D Morphable Face Models – Past, Present, and Future. ACM ToG 39, 5 (2020), 157:1–157:38.Google ScholarDigital Library
    H. Feng, T. Bolkart, J. Tesch, M. J. Black, and V. Abrevaya. 2022. Towards Racially Unbiased Skin Tone Estimation via Scene Disambiguation. https://arxiv.org/abs/2205.03962Google Scholar
    Y. Feng, H. Feng, M. J. Black, and T. Bolkart. 2021. Learning an Animatable Detailed 3D Face Model from In-the-Wild Images. ACM ToG 40, 4 (2021), 88:1–88:13.Google ScholarDigital Library
    H. Kim, M. Zollhöfer, A. Tewari, J. Thies, C. Richardt, and C. Theobalt. 2018. InverseFaceNet: Deep monocular inverse face rendering. In CVPR. 4625–4634.Google Scholar
    T. Li, T. Bolkart, M. J. Black, H. Li, and J. Romero. 2017. Learning a model of facial shape and expression from 4D scans. ACM ToG 36, 6 (2017), 194:1–194:17.Google ScholarDigital Library
    N. Mehrabi, F. Morstatter, N. Saxena, K. Lerman, and A. Galstyan. 2021. A Survey on Bias and Fairness in Machine Learning. ACM Comput. Surv. 54, 6 (2021).Google ScholarDigital Library
    R. Ramamoorthi and P. Hanrahan. 2001. A signal-processing framework for inverse rendering. In SIGGRAPH. 117–128.Google Scholar
    J. Shang, T. Shen, S. Li, L. Zhou, M. Zhen, T. Fang, and L. Quan. 2020. Self-Supervised Monocular 3D Face Reconstruction by Occlusion-Aware Multi-view Geometry Consistency. In ECCV, Vol. 12360. 53–70.Google Scholar

ACM Digital Library Publication:


Overview Page: