FIT: A Large-Scale Dataset for Fit-Aware Virtual Try-On
2026-04-09 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionGraphics
AI summaryⓘ
The authors created a big dataset to help computers better show how clothes actually fit people, like showing if a shirt is too big or too small. They used 3D models and physics to simulate how clothes drape, then turned those simulations into realistic images while keeping the person's look consistent. Their dataset includes accurate body and garment measurements, which was missing before. They also trained a new model that can realistically show different fits, improving over past virtual try-on methods. The data and code will be shared publicly to help others build on their work.
Virtual try-onGarment fit3D garment simulationPhysics-based drapingRe-texturingPerson identity preservationSynthetic datasetComputer visionPhotorealistic rendering
Authors
Johanna Karras, Yuanhao Wang, Yingwei Li, Ira Kemelmacher-Shlizerman
Abstract
Given a person and a garment image, virtual try-on (VTO) aims to synthesize a realistic image of the person wearing the garment, while preserving their original pose and identity. Although recent VTO methods excel at visualizing garment appearance, they largely overlook a crucial aspect of the try-on experience: the accuracy of garment fit -- for example, depicting how an extra-large shirt looks on an extra-small person. A key obstacle is the absence of datasets that provide precise garment and body size information, particularly for "ill-fit" cases, where garments are significantly too large or too small. Consequently, current VTO methods default to generating well-fitted results regardless of the garment or person size. In this paper, we take the first steps towards solving this open problem. We introduce FIT (Fit-Inclusive Try-on), a large-scale VTO dataset comprising over 1.13M try-on image triplets accompanied by precise body and garment measurements. We overcome the challenges of data collection via a scalable synthetic strategy: (1) We programmatically generate 3D garments using GarmentCode and drape them via physics simulation to capture realistic garment fit. (2) We employ a novel re-texturing framework to transform synthetic renderings into photorealistic images while strictly preserving geometry. (3) We introduce person identity preservation into our re-texturing model to generate paired person images (same person, different garments) for supervised training. Finally, we leverage our FIT dataset to train a baseline fit-aware virtual try-on model. Our data and results set the new state-of-the-art for fit-aware virtual try-on, as well as offer a robust benchmark for future research. We will make all data and code publicly available on our project page: https://johannakarras.github.io/FIT.