3D object detection has recently become popular due to many applications in robotics, augmented reality, autonomy, and image retrieval.
Ranked #2 on Monocular 3D Object Detection on Google Objectron
Our tracker is capable of performing relative-scale 9-DoF tracking in real-time on mobile devices.
We present Attention Mesh, a lightweight architecture for 3D face mesh prediction that uses attention to semantically meaningful regions.
We present a simple, real-time approach for pupil tracking from live video on mobile devices.
Performance evaluation demonstrates that on out-of-cache inputs on an Intel Skylake-X processor the new Two-Pass algorithm outperforms the traditional Three-Pass algorithm by up to 28% in AVX512 implementation, and by up to 18% in AVX2 implementation.
We present a novel approach for neural network-based hair segmentation from a single camera input specifically designed for real-time, mobile application.
We design an Enriched Deep Recurrent Visual Attention Model (EDRAM) - an improved attention-based architecture for multiple object recognition.
In recent years, text recognition has achieved remarkable success in recognizing scanned document text.