On Fairness in Face Albedo Estimation

被引：1

作者：

Feng, Haiwen ^{[1
]}

Bolkart, Timo ^{[1
]}

Tesch, Joachim ^{[1
]}

Black, Michael J. ^{[1
]}

Abrevaya, Victoria ^{[1
]}

机构：

[1] MPI Intelligent Syst, Tubingen, Germany

来源：

PROCEEDINGS SIGGRAPH 2022 TALKS | 2022年

关键词：

SKIN COLOR;

D O I：

10.1145/3532836.3536281

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

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 amelio-rated by recent advances, improving fairness in albedo estimation.

引用

页数：2

共 12 条

[1] A morphable model for the synthesis of 3D faces
Blanz, V
Vetter, T
[J]. SIGGRAPH 99 CONFERENCE PROCEEDINGS, 1999, : 187 - 194
[2] Buolamwini J., 2018, PMLR, P77
[3] SKIN COLOR TYPOLOGY AND SUNTANNING PATHWAYS
CHARDON, A
CRETOIS, I
HOURSEAU, C
[J]. INTERNATIONAL JOURNAL OF COSMETIC SCIENCE, 1991, 13 (04) : 191 - 208
[4] Variations in skin colour and the biological consequences of ultraviolet radiation exposure
Del Bino, S.
Bernerd, F.
[J]. BRITISH JOURNAL OF DERMATOLOGY, 2013, 169 : 33 - 40
[5] 3D Morphable Face Models-Past, Present, and Future
Egger, Bernhard
Smith, William A. P.
Tewari, Ayush
Wuhrer, Stefanie
Zollhoefer, Michael
Beeler, Thabo
Bernard, Florian
Bolkart, Timo
Kortylewski, Adam
Romdhani, Sami
Theobalt, Christian
Blanz, Volker
Vetter, Thomas
[J]. ACM TRANSACTIONS ON GRAPHICS, 2020, 39 (05):
[6] Feng HW, 2022, Arxiv, DOI arXiv:2205.03962
[7] Learning an Animatable Detailed 3D Face Model from In-The-Wild Images
Feng, Yao
Feng, Haiwen
Black, Michael J.
Bolkart, Timo
[J]. ACM TRANSACTIONS ON GRAPHICS, 2021, 40 (04):
[8] Jiaxiang Shang, 2020, Computer Vision - ECCV 2020. 16th European Conference. Proceedings. Lecture Notes in Computer Science (LNCS 12360), P53, DOI 10.1007/978-3-030-58555-6_4
[9] InverseFaceNet: Deep Monocular Inverse Face Rendering
Kim, Hyeongwoo
Zollhoefer, Michael
Tewari, Ayush
Thies, Justus
Richardt, Christian
Theobalt, Christian
[J]. 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, : 4625 - 4634
[10] Learning a model of facial shape and expression from 4D scans
Li, Tianye
Bolkart, Timo
Black, Michael J.
Li, Hao
Romero, Javier
[J]. ACM TRANSACTIONS ON GRAPHICS, 2017, 36 (06):

← 1 2 →