eBay on Wednesday announced that its mainland mobile app for iPhone, iPad and iPod touch will be gaining advanced image-based search and discovery features via an update this fall.
Powered by computer vision and deep learning, the upcoming features will make the entire Internet “shoppable with just the snap of a photo,” said eBay.
For instance, you will be able to snap a photo of a random person on the street wearing something you wanted to buy but didn’t know where to get it, or use an existing photo from the Camera roll, or share images from any web browser or social platform like Pinterest.
The mobile app will analyze your image and sift through the more than 1.1 billion listings on eBay to find any matching products on the service.
“All you have to do is share the image with eBay and our mobile app will find listings of the item in that image or others like it,” said the company. “Then, we’ll show you listings that match the item you are looking for.”
The video embedded below shows off the upcoming features in action.
And here’s how this technology works:
When you upload images to run Find It On eBay and Image Search, we use a deep learning model called a convolutional neural network to process the images. The output of the model gives us a representation of the your image that we can use to compare to the images of the live listings on eBay.
Then, we rank the items based on visual similarity and use our open-source Kubernetes platform to quickly bring these results to you, wherever you are in the world.
As mentioned, the new features will roll out to eBay for iOS starting this fall. The company has also said it expects to launch more computer vision products in the coming months.