Automatically designing an image processing pipeline for a five-band camera prototype using the local, linear, learned (L3) method

Local Linear Approximation for Camera Image Processing Pipelines

Modern digital cameras include an image processing pipeline that converts raw sensor data to a rendered RGB image. Several key steps in the pipeline operate on spatially localized data (demosaicking, noise reduction, color conversion). We show how to derive a collection of local, adaptive linear filters (kernels) that can be applied to each pixel and its neighborhood; the adaptive linear calcul...

Local Linear Learned Image Processing Pipeline

The local linear learned (L3) algorithm is presented that simultaneously performs the demosaicking, denoising, and color transform calculations of an image processing pipeline for a digital camera with any color filter array. © 2011 Optical Society of America OCIS codes: 040.1490, 100.2000.

Efficient illuminant correction in the local, linear, learned (L3) method

To speed the development of novel camera architectures we proposed a method, L (Local, Linear and Learned), that automatically creates an optimized image processing pipeline. The L method assigns each sensor pixel into one of 400 classes, and applies class-dependent local linear transforms that map the sensor data from a pixel and its neighbors into the target output (e.g., CIE XYZ rendered und...

Automating the design of image processing pipelines for novel color filter arrays: local, linear, learned (L3) method

Automating the design of image processing pipelines for novel color filter arrays: Local, Linear, Learned (L) method

The high density of pixels in modern color sensors provides an opportunity to experiment with new color filter array (CFA) designs. A significant bottleneck in evaluating new designs is the need to create demosaicking, denoising and color transform algorithms tuned for the CFA. To address this issue, we developed a method(local, linear, learned or L) for automatically creating an image processi...