JOURNAL
Ideas, experiments and what we’re learning.
Essays on the problems we work on: how virtual try-on got here, what makes fabric hard, how to measure fidelity, and how to build it responsibly. Every claim about the field links to its source.
A short history of virtual try-onFrom warping a product photo onto a body to diffusion models that learn where every thread should go: how the field got here, and what is still unsolved.
Why fabric is harder than pixelsTexture, print, material and drape: the properties of cloth that make try-on a physical problem, not just an image problem.
Evaluating texture fidelity in VTOWhat FID, LPIPS, SSIM and DISTS actually measure, why none of them is enough on its own, and a framework for measuring whether the shirt still looks like the shirt.
Pose consistency in garment generationWhy one good frame isn’t enough, and what it takes to keep a garment the same across poses, views and video.
Fast enough for a storefrontDiffusion models are slow by design. How step distillation works, what it costs in detail, and why speed is a research problem for try-on.
Where training data comes fromMost public try-on datasets are licensed for research only. Why provenance, consent and privacy shape how a commercial try-on model has to be built.JOIN THE RESEARCH TEAM
Work on the open problems with us.
Students, researchers and engineers. The application takes about two minutes.