High quality Debayer with MG (Multiple Gradients) algorithm on GPU
Updated:
Fastvideo company has released high quality debayer on CUDA.
Fastvideo company after years of R&D has released new high quality debayer algorithm on CUDA. Fastvideo has put together their research results, experience in GPU image & video processing, knowledge of NVIDIA CUDA technology and software optimization methods to release high quality demosaicing algorithm.
In general, debayer algorithm is the most important part of any image processing pipeline for RAW data. Quality of image processing is mostly relied on debayer and our MG algorithm can do that job in fast and efficient way. This is quite complicated algorithm which takes into account neighbour pixels in the vicinity 23 x 23. For example, 16-bit 4K raw image with resolution 3840 x 2160 could be debayered within 1.6 ms on NVIDIA GeForce GTX 1080 GPU. That performance comes from powerfull NVIDIA hardware and from highly optimized massive parallel implementation of MG demosaicing algorithm from Fastvideo.
MG debayer from Fastvideo is available as standalone library or as a part of GPU Image & Video Processing SDK for Windows and Linux. Demo version of MG debayer for NVIDIA GPU is available from Fastvideo website and works under 64-bit Windows. Fastvideo SDK trial is available upon request.
About Fastvideo
Fastvideo was founded in 2009 in Dubna, Russia. Company is specializing in GPU image and video processing. The most powerful product from Fastvideo is high performance SDK for real-time image and video processing on NVIDIA GPU. That SDK is the ground for other super fast GPU-based solutions for demosaicing, denoising, tone mappping, resizing, JPEG and JPEG2000 encoding and decoding, CinemaDNG processing, etc.
Links
Product page: Fastvideo Debayer with MG algorithm on CUDA
About the author
Fyodor Serzhenko, PhD, is the founder and CEO of Fastvideo. He earned his PhD at the Moscow Institute of Physics and Technology (MIPT) in 1993. Since 2009 he has led the development of Fastvideo’s GPU-accelerated image codecs and ISP modules, including the Fastvideo SDK. Connect on LinkedIn.
Why you can trust these results
Fastvideo has built GPU-accelerated image processing software since 2009. Our codecs comply with the standards they implement — JPEG (ITU-T T.81 / ISO IEC 10918) and JPEG2000 (ITU-T T.800 / ISO IEC 15444) — and our tools are open source on GitHub. Every performance figure we publish is reproducible: see our benchmark methodology, download the Fastvideo SDK benchmark report (PDF), and measure it on your own GPU.