Our Augmented Reality Platform explained
Augmented Reality SDK ~ Why Did We Build it?
The DeepAR Augmented Reality SDK is made for developers who want to add the highest quality, mobile optimised, Snapchat and Facebook style 3D and realistic face lenses, masks and special FX to iOS, Android, HTML5 and Unity applications. The best part is that the DeepAR SDK can be integrated in a matter of minutes, and supports hundreds of masks, lenses, effects, and filters. Our team is also ready to help you create amazing new content for your platform.
DeepAR Realtime Face Detection
The DeepAR Augmented Reality SDK and platform detects faces and facial features, using a variety of proprietary data models, and also advanced machine learning in 3D. It has extremely fast and precise face detection, fast and robust eye, nose and chin detection. It detects more than 68 facial feature points at up to 60 frames per second.
DeepAR is optimised to detect multiple faces in realtime, specifically on mobile devices.
DeepAR Real Time Face Tracking
The DeepAR Augmented Reality platform also includes robust, realtime face and head-tracking. DeepAR can track any face under almost light conditions from any angle, even when the head is turned 180 degrees either side.
DeepAR can track multiple faces in realtime with high performance, and is optimised for lower end smartphones.
DeepAR Rendering Engine
DeepAR has also developed a high performance, cross platform, rendering engine optimised for mobile devices and browsers applications. It delivers outstanding performance even on lower specification Android smartphones.
DeepAR Studio allows you to focus on creating incredible assets rather than focusing on building a complex Augmented Reality technology platform. The DeepAR Studio allows you to use existing software like Maya and Blender to create deformable and rigid objects, video filters, video effects, animated and morphing objects, as well as particle effects. It enables super fast asset creation and testing.
Multiple Face Detection
The DeepAR SDK is optimised to detect multiple faces in realtime. Currently we are optimised to detect and track up to four face simultaneously but more are possible. Stay tuned.
Realtime Emotion Detection
DeepAR also has realtime emotion detection based on proprietary neural network and deeplearning models. Now you can detect all the core emotions – Anger – Disgust – Fear – Happy – Sad – Surprise – Neutral – in real time, and all optimised for mobile applications