Search Results for author:
Found 5 papers, 0 papers with code
SemifreddoNets: Partially Frozen Neural Networks for Efficient Computer Vision Systems
The hardware implementation of SemifreddoNets provides up to an order of magnitude reduction in silicon area and power consumption as compared to their equivalent implementation on a general-purpose accelerator.
A Machine Learning Imaging Core using Separable FIR-IIR Filters
We use a fully trainable, fixed-topology neural network to build a model that can perform a wide variety of image processing tasks.
VisionISP: Repurposing the Image Signal Processor for Computer Vision Applications
However, optimal perceptual image quality does not always translate into optimal performance for computer vision applications.
Eye Contact Correction using Deep Neural Networks
We propose an eye contact correction model that restores the eye contact regardless of the relative position of the camera and display.
Automatic ISP image quality tuning using non-linear optimization
These need to be hand tuned by Image Quality (IQ) experts, which takes considerable amount of time.
