Computer vision
Teaching machines to interpret and reason about the visual world, from object recognition to medical imaging.
Project
SemanticPaint: Interactive 3D Labeling and Learning at your Fingertips
We present a new interactive approach to 3D scene understanding. Our system, SemanticPaint, allows users to simultaneously scan their environment, whilst interactively segmenting the scene simply by reaching out and touching any desired object or…
Publication
Computationally Bounded Retrieval
Microsoft Research Blog
Microsoft researchers accelerate computer vision accuracy and improve 3D scanning models
Posted by George Thomas Jr. You may already have heard about the Microsoft technology that can automatically identify objects in a picture and write an accurate caption for it, but those types of research advancements…