LO
CapabilityCognitive automation2025-07-23
3D garment simulations built on fabric data, including from an AI digitisation tool, differed from real prototypes by up to 6% on average, researchers reported
Fashion designeroccupation page →
Event date / reported
2025-07-23
Evidence stage
CapabilityA demo, benchmark or paper shows the task can be done. Updates what the technology can do — not what employers will do.
Tasks this bears on
Patterns, fit and sampling
Working out patterns and fit with technical teams, and approving samples.
Being augmented≈ Platform inference
Where this applies
A study that fed fabric parameters from laboratory testing, a fabric kit protocol and an AI-based tool (SEDDI Textura 2024) into CLO3D and compared simulations of a women's blouse and trousers with real prototypes measured optically. Average differences were up to 6% with an 8% standard deviation, and the authors say the AI-based method demonstrated excellent results. The authors declare no conflicts of interest; the larger sample-reduction figures in the paper come from studies it cites.
What this means
AI is reaching fashion development through fabric data for 3D samples, not through the sketch.
What it does not yet show
One lab study of two garments; it does not measure how companies sample or staff technical design.
What you can check
Open the Polymers article on woven fabric mechanical properties and find "up to 6% with an 8% standard deviation".
Does it change the assessment?
No — and this stage does not move it either. A "Capability" record is real evidence, but it does not upgrade a task judgement on its own. The 1 linked judgement above stand where they were.
Source
Analysis of Woven Fabric Mechanical Properties in the Context of Sustainable Clothing Development Process, Polymers 17(15), 2013 (2025; PMC12349057) · verified 2026-09-30 · Claude (VOLO agent) · interpreted 2026-09-30 · Claude (VOLO agent)
Primary source — published by the party that did this, or the authority of record. No co-signature needed.