“Evaluating Skin Tone Biases in Virtual Human Rendering” by Menezes, Leal, Moura, Araujo and Musse
Conference:
Type(s):
Title:
- Evaluating Skin Tone Biases in Virtual Human Rendering
Session/Category Title:
- Rendering
Presenter(s)/Author(s):
Abstract:
We present a comparative analysis of skin tone rendering in MetaHuman avatars using real-world and reference-based color inputs, revealing systematic differences across the Monk Skin Tone scale and highlighting key limitations in current real-time rendering pipelines for darker and intermediate skin tones.
References:
[1] Victor Flávio de Andrade Araujo, Angelo Brandelli Costa, and Soraia Raupp Musse. 2023. Evaluating the uncanny valley effect in dark colored skin virtual humans. In 2023 36th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI). IEEE, 1–6.
[2] Courtney M Heldreth, Ellis P Monk, Alan T Clark, Candice Schumann, Xango Eyee, and Susanna Ricco. 2024. Which skin tone measures are the most inclusive? An investigation of skin tone measures for artificial intelligence. ACM Journal on Responsible Computing 1, 1 (2024), 1–21.
[3] Mason Khoo, Dan Lipson, and Jose Velasquez. 2023. Lighting and Look Dev for Skin Tones in Disney’s” Strange World”. In Proceedings of the 2023 Digital Production Symposium. 1–5.
[4] Theodore Kim, Holly Rushmeier, Julie Dorsey, Derek Nowrouzezahrai, Raqi Syed, Wojciech Jarosz, and AM Darke. 2022. Countering racial bias in computer graphics research. In ACM SIGGRAPH 2022 Talks. 1–2.
[5] Ellis Monk. 2019. The monk skin tone scale. (2019).
[6] Pisut Wisessing and Rachel McDonnell. 2024. Blinded by the light: Does portrait lighting design affect perception of realistic virtual humans?. In ACM Symposium on Applied Perception 2024. 1–10.
