# Countering Racial Bias in Computer Graphics Research

arXiv: https://arxiv.org/abs/2103.15163 · HTML: https://mlsanity.com/paper/2103.15163/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Mar 2021.

## Built on by (most cited first, 8 of 8)

- [Towards Racially Unbiased Skin Tone Estimation via Scene Disambiguation](https://mlsanity.com/paper/2205.03962/) (2022)
- [SynthLight: Portrait Relighting with Diffusion Model by Learning to Re-render Synthetic Faces](https://mlsanity.com/paper/2501.09756/) (2025)
- [Towards Better User Studies in Computer Graphics and Vision](https://mlsanity.com/paper/2206.11461/) (2022)
- [Hairmony: Fairness-aware hairstyle classification](https://mlsanity.com/paper/2410.11528/) (2024)
- [Parametric Shadow Control for Portrait Generation in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2503.21943/) (2025)
- [A Counterfactual Fair Model for Longitudinal Electronic Health Records via Deconfounder](https://mlsanity.com/paper/2308.11819/) (2023)
- [POLAR: A Portrait OLAT Dataset and Generative Framework for Illumination-Aware Face Modeling](https://mlsanity.com/paper/2512.13192/) (2025)
- [True to Tone? Quantifying Skin Tone Fidelity and Bias in Photographic-to-Virtual Human Pipelines](https://mlsanity.com/paper/2604.02055/) (2026)

## Abstract (arXiv)

Current computer graphics research practices contain racial biases that have resulted in investigations into "skin" and "hair" that focus on the hegemonic visual features of Europeans and East Asians. To broaden our research horizons to encompass all of humanity, we propose a variety of improvements to quantitative measures and qualitative practices, and pose novel, open research problems.