Spatial Understanding Powered by Synthetic Data


About LexSet:
LexSet is a visual AI solution for object recognition and visual search, specialized in synthetic data generation. Our clients range from furniture retailers to industrial and robotics companies. In short, we’re good at recognizing and describing objects in images and real-time space, and if there’s no good data to train with, we create it.

Our first offerings are in retail where the most common use for our API is for retailers to enable their shoppers to search with photos using “LexSet Visual Search,” LVS allows shoppers to search for items that look similar to what’s in any scene. LexSet also offers retailers related applications including “Similar Product Search” and “Shoppable Galleries.”

Today, LexSet uses synthetic data to build and improve systems for companies ranging from retailers to industrial part manufacturers and robotics companies. For customers who have trouble finding or producing the data needed to power computer vision systems, we’ve pioneered a technique to create ‘synthetic data’ from 3D models of objects. We use models of objects and render them thousands of times in all possible lighting conditions, backgrounds, and camera angles- giving us near infinite data with which to “teach” our AI.