What Matters in Image-based Cloth Size Estimation?
| dc.contributor.advisor | Escalera Guerrero, Sergio | |
| dc.contributor.author | Teker, Izel | |
| dc.date.accessioned | 2026-10-27T13:19:38Z | |
| dc.date.available | 2026-10-27T13:19:38Z | |
| dc.date.issued | 2026-06-28 | |
| dc.description | Treballs finals del Màster de Fonaments de Ciència de Dades, Facultat de matemàtiques, Universitat de Barcelona. Any: 2026. Tutor: Sergio Escalera | |
| dc.description.abstract | Estimating garment measurements from a single photograph is a supervised learning problem starved of supervision: real sizing charts are produced by hand and exist only at the scale of a few hundred garments, while the synthetic corpora large enough to train deep models carry no measurement labels. This thesis connects the two. I build an automated pipeline1 that derives physical measurements directly from the 3D garment meshes of SewFactory, producing a large-scale synthetic measurement dataset aligned to the 19-dimensional MV-Fashion schema and combinable with the real corpus. Using this hybrid data, I ask what matters for image-based garment size estimation, and isolate three factors. First, data composition is the dominant controllable factor: hybrid synthetic–real training improves on a real-only baseline, most strongly in the garment groups where real annotation is scarcest. This holds despite measurable noise in the synthetic labels, and a controlled probe shows the residual synthetic–real gap to be one of label quality and coverage, not image appearance. Second, a pose-canonicalisation stage inherited from sewing-pattern reconstruction does not transfer to measurement: added as a frozen pixel-fidelity pre-processor it degrades accuracy, because it smooths away the free-raping geometry the measurements depend on. Third, for the hardest dimensions the binding constraint is the single near-frontal view itself, which no amount of data can overcome. The broader contribution is methodological: for this task synthetic data is worth having for its labels and coverage rather than as an appearance bridge, and a preprocessor optimised for one task does not transfer for free to another whose objective differs. | |
| dc.format.extent | 25 p. | |
| dc.format.mimetype | application/pdf | |
| dc.identifier.uri | https://hdl.handle.net/2445/232388 | |
| dc.language.iso | eng | |
| dc.rights | cc-by-nc-nd (c) Teker, Izel, 2026 | |
| dc.rights.accessRights | info:eu-repo/semantics/openAccess | |
| dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/3.0/es/ | |
| dc.subject.classification | Mesuraments físics | |
| dc.subject.classification | Processament d'imatges | |
| dc.subject.classification | Treballs de fi de màster | |
| dc.subject.other | Physical measurements | |
| dc.subject.other | Image processing | |
| dc.subject.other | Master's thesis | |
| dc.title | What Matters in Image-based Cloth Size Estimation? | |
| dc.type | info:eu-repo/semantics/masterThesis |
Fitxers
Paquet original
1 - 1 de 1