Learning the image processing pipeline

Abstract

Many creative ideas are being proposed for image sensor designs, and these may be useful in applications ranging from consumer photography to computer vision. To understand and evaluate each new design, we must create a corresponding image processing pipeline that transforms the sensor data into a form that is appropriate for the application. The need to design and optimize these pipelines is time-consuming and costly. We explain a method that combines machine learning and image systems simulation that automates the pipeline design. The approach is based on a new way of thinking of the image processing pipeline as a large collection of local linear filters. We illustrate how the method has been used to design pipelines for novel sensor architectures in consumer photography applications.

Cited by in corpus (11)

• DeepISP: Towards Learning an End-to-End Image Processing Pipeline
• Learning to See in the Dark
• Exploit Camera Raw Data for Video Super-Resolution via Hidden Markov Model Inference
• CameraNet: A Two-Stage Framework for Effective Camera ISP Learning
• Towards Real Scene Super-Resolution with Raw Images
• Exploiting Raw Images for Real-Scene Super-Resolution
• Data-Driven Design for Fourier Ptychographic Microscopy
• Neural Imaging Pipelines - the Scourge or Hope of Forensics?
• Validation of image systems simulation technology using a Cornell Box
• BLADE: Filter Learning for General Purpose Computational Photography
• Neural Camera Simulators