FIT: A Large-Scale Dataset for Fit-Aware Virtual Try-On
Johanna Karras, Yuanhao Wang, Yingwei Li, Ira Kemelmacher-Shlizerman
2026-04-10
Summary
This paper introduces a new dataset and model for virtual try-on, focusing on making the clothes actually *fit* the person in the image, not just look like they're wearing something. It's about creating realistic images of people trying on clothes online.
What's the problem?
Current virtual try-on technology is good at making clothes *look* like they're on someone, but it doesn't accurately show how clothes fit different body types. For example, it won't show what an oversized shirt looks like on a small person, or how tight a small shirt would be on a large person. This is because there aren't enough datasets available with detailed information about both clothing and body sizes, especially for clothes that don't fit well.
What's the solution?
The researchers created a large dataset called FIT, with over a million images of people 'trying on' clothes. They didn't use real photos for everything; instead, they used computer graphics to create realistic 3D clothes and simulate how they would drape on different bodies. Then, they used a special technique to make these computer-generated images look like real photos, while still keeping the accurate size and shape information. They also trained a virtual try-on model using this new dataset to make it better at showing realistic fit.
Why it matters?
This work is important because it addresses a major flaw in current virtual try-on systems. By focusing on accurate fit, it makes online clothes shopping more realistic and helpful. The new dataset and model provide a benchmark for future research in this area, and the publicly available data and code will allow other researchers to build upon this work and create even better virtual try-on experiences.
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.