Research

FlexISP: A Flexible Camera Image Processing Framework

"FlexISP: A Flexible Camera Image Processing Framework"
Felix Heide (UBC), Markus Steinberger (TU Graz), Yun-Ta Tsai (NVIDIA), Mushfiqur Rouf (UBC), Dawid Pająk (NVIDIA), Dikpal Reddy (NVIDIA), Orazio Gallo (NVIDIA), Jing Liu (UC Santa Cruz), Wolfgang Heidrich (KAUST), Karen Egiazarian (TUT), Jan Kautz (NVIDIA), Kari Pulli (NVIDIA), in Proc. ACM SIGGRAPH Asia, December 2014
Research Area: Computational Photography
Author(s): Felix Heide (UBC), Markus Steinberger (TU Graz), Yun-Ta Tsai (NVIDIA), Mushfiqur Rouf (UBC), Dawid Pająk (NVIDIA), Dikpal Reddy (NVIDIA), Orazio Gallo (NVIDIA), Jing Liu (UC Santa Cruz), Wolfgang Heidrich (KAUST), Karen Egiazarian (TUT), Jan Kautz (NVIDIA), Kari Pulli (NVIDIA)
Date: December 2014
Download(s):
Submission video (YouTube)Additional results (html)Paper supplement (pdf)FlexISP demosaicking demo (source code)
 
Abstract: Conventional pipelines for capturing, displaying, and storing images are usually defined as a series of cascaded modules, each responsible for addressing a particular problem. While this divide-and-conquer approach offers many benefits, it also introduces a cumulative error, as each step in the pipeline only considers the output of the previous step, not the original sensor data. We propose an end-to-end system that is aware of the camera and image model, enforces natural-image priors, while jointly accounting for common image processing steps like demosaicking, denoising, deconvolution, and so forth, all directly in a given output representation (e.g., YUV, DCT). Our system is flexible and we demonstrate it on regular Bayer images as well as images from custom sensors. In all cases, we achieve large improvements in image quality and signal reconstruction compared to state-of-the-art techniques. Finally, we show that our approach is capable of very efficiently handling high-resolution images, making even mobile implementations feasible.