This week in Wayfair Data Science’s explainer series, Senior Machine Learning Engineer Tim Zhang lays out what you need to know about training image synthesis. Training image synthesis is a fairly young project for the Computer Vision team at Wayfair. We have explored a few different use cases that can take advantage of this approach, such as search-with-photo, image-based 3D geometry generation, and camera perspective estimation. Looking forward, we are aiming at faster rendering speed and more intelligent domain randomization.
Yuxuan (Tim) Zhang received his MS in Predictive Analytics at DePaul University. He is currently a Senior Machine Learning Engineer on Wayfair Data Science’s Computer Vision team, with a primary focus on 3D machine learning. He enjoys working with like-minded individuals to unlock opportunities in computer vision/graphics. In his spare time, Tim enjoys outdoor sports such as skiing, skating and dragon boating. He also runs a meetup group called Boston Computational Creativity, which brings on demos and facilitates discussions around the intersection between art, creativity and technology.
