Google Shopping: How AI’s Virtual Try-On Transforms the Way We Shop for Clothes

Google Shopping introduces a new feature for women’s clothing that will use Generative AI to enable online shoppers to virtual try on clothes before buying them online.

Have you ever wondered if you could also try out clothes you’re shopping for online before actually buying them? The latest feature by Google Shopping does exactly the job for you! The company introduced two unique features that use Generative AI technology to allow you to find out exactly the clothes you’re looking for and virtually try them before purchasing them.

Google Shopping aims to bring the trial room experience to online shoppers so they can visualize what a piece of clothing will look like on theme and eliminate the hassle of ordering ill-fitted clothes online.

“So today we’re introducing two new features that bring this fitting room experience to you: Virtual try-on for apparel uses generative AI to show you clothes on a wide selection of real models, while new filters help you find exactly what you’re looking for.”

Virtual Try-On and Refinements for Apparel

The virtual try-on feature is powered by Google’s new diffusion-based model including text-to-art generators: Stable Diffusion, and DALL-E 2. These diffusion models learn to eliminate the noise from an image. They’re trained using pairs of images consisting of models wearing an article of clothing in two different poses.

Google, in their blog post, explained, “Virtual try-on for apparel shows you how clothes look on a variety of real models. Here’s how it works: Our new generative AI model can take just one clothing image and accurately reflect how it would drape, fold, cling, stretch, and form wrinkles and shadows on a diverse set of real models in various poses. We selected people ranging in sizes XXS-4XL representing different skin tones, body shapes, ethnicities, and hair types.”

The feature which allows you to see apparel on different types of skin tones or in different sizes has started rolling out for the US shoppers for women’s clothing on select leading brands like H&M, Anthropologie, LOFT, etc, across Google.

Another feature of Google Shopping is the all-new guided refinements options. With the help of machine learning and new visual matching algorithms, you can use filters like color, size, pattern, price, style, etc. to specify your preference while searching for clothes online.

“Do you like that top, but want a less pricey version? Or this jacket, but in a different pattern? Associates can help with this in a store, suggesting and finding other options based on what you’ve already tried on. Now you can get that extra hand when you shop for clothes online.”- Google’s blog post.

Google’s Shopping Graph is a data set of the world’s shopping information that helps to find exactly the products they’re searching for using specific standards. The Shopping Graph has more than a whopping 35 billion product listings. Google uses the Graph to provide helpful shopping features to customers using natural language understanding.

However,  these virtual try-on and refinement features are nothing new for Google. It has collaborated with companies like MAC Cosmetics, L’Oréal, and others by providing them with a try-on feature that allowed them to choose their favorite shades of cosmetics while shopping online.

Also, these features are already being experimented with by leading tech companies and are even already available across shopping apps like Amazon and Walmart.

Google Shopping has mentioned that it would bring the technology to more brands shortly and will also make the feature available for men’s clothing soon.

Google is aiming to build something more superior using Generative AI technology this time. The company says it wants to ease the shopping experience of online shoppers by providing them with unique features using advanced technology to grow their confidence while shopping online.