True to Tone? Quantifying Skin Tone Fidelity and Bias in Photographic-to-Virtual Human Pipelines

Dimensions overall score 4.0

GitHub Code Pulse

No public code linked for this paper yet.

• The proposed methodology for evaluating skin tone fidelity in Virtual Human generation pipelines is fully automatic and scalable.method 95%
• The pipeline achieves low computational cost and enables large-scale evaluation by avoiding learning or training stages.technical 90%
• Skin tone extraction shows phenotype-dependent behavior across different extraction strategies.result 85%
• Darker skin tones consistently show higher colorimetric errors in Virtual Human rendering pipelines.result 90%
• The methodology evaluates approximately 19,848 rendered instances for comprehensive analysis.method 95%
• Skin tone consistency is evaluated objectively using CIELAB color space with ΔE metric and Individual Typology Angle (ITA).method 90%
• Most accessible avatar creation pipelines lack colorimetric calibration, which can introduce inconsistencies and bias.limitation 85%
• The methodology integrates skin color and illumination extraction, texture recolorization, real-time rendering, and quantitative color analysis.method 90%

Competitive landscape

Competitor map is still being generated for this paper. Enable generation or check back soon.

Startup potential card