News Technology news CUDA GPU Solution drastically increases performance of cameras

Compact camera CMOSIS CMV20000 PCI Express 20 Mpix

New software partner provides incredible options for image processing on GPU


Software collaboration

XIMEA always strives to offer to customers something extra on top of everything else.

We call it - To go the extra Vision.

This is why cooperation with the company called Fastvideo was so important for us.

You can explore the new possibilities below.


Audio/video sessions from GTC 2014 Conference on the topic:

WATCH Overview: Full Image Processing Pipeline on  the GPU for Camera Applications.pdf
WATCH Pro version: Full Image Processing Pipeline on the GPU for Camera Applications.pdf
WATCH GPU benchmarks: Latest (2018) image processing benchmarks from Fastvideo for NVIDIA GeForce GTX 980, 1080 and Tegra X1

Fastvideo Image Processing SDK

Fastvideo company has designed high performance SDK to offer full image processing pipeline on GPU for camera applications with total peak performance 4 GPix/s.
For example, JPEG encoding for 24-bit image with resolution 4K could be done at 0.8 ms on NVIDIA GeForce GTX 1080 GPU.
This SDK corresponds to standard image and video processing pipeline for camera applications.
It covers all image processing stages starting from raw image acquisition from a camera to JPEG or JPEG2000 compression with storage to RAM or SSD/HDD.
Currently, Fastvideo offers the fastest on the market solutions for demosaicing, denoising, resizing, JPEG and JPEG2000 encoding on GPU.
Designed for NVIDIA CUDA develop fast high speed

Image & Video Processing SDK Features

  • Image acquisition module from a camera
  • Unpacking module for various RAW formats
  • Dark frame subtraction (FPN)
  • Flat-Field Correction (Shading Correction)
  • White Balance
  • Exposure correction
  • RAW denoiser
  • High quality debayer
  • Color noise removal
  • Color correction with matrix
  • RGB and HSL tone mapping with LUTs (curves and levels)
  • Rotation to any arbitrary angle
  • Crop
  • Resize
  • Sharp
  • DCP profile support
  • 3D LUTs (RGB and HSV) for output transform
  • LCP profile support
  • RGB Histogram and Parade (waveform monitor)
  • Scaling and output to monitor via OpenGL (video player)
  • JPEG codec
  • RAW Bayer codec
  • JPEG 2000 codec

GPU CUDA benchmarks GeForce GTX 1080

Image & Video Processing SDK Options

  • Auto White Balance
  • Discrete Wavelet transforms 5/3 and 9/7
  • Medial filter
  • Time measurements for all SDK modules
  • Trace module
  • Multiplexor module
  • Support for input data from HD-SDI grabbers: Bluefish and Deltacast
  • Multiple camera solutions for real-time processing
  • NVIDIA Tegra K1, X1 and X2 support
  • Stream-per-thread option for better performance
  • Interoperability with third-party SDKs on CUDA
  • Interoperability with FFmpeg
  • RAW and DNG (CinemaDNG) image and video processing
Fast compression and realtime image and video processing on GPU is popular and growing in demand in modern industries.

Indeed, high framerate cameras, real-time video surveillance systems, 3D, VR and digital cinema solutions, heavy-loaded web services and medical equipment, often require zero tolerance to delays due to image processing.

And this is where the performance of image and video processing could be a serious bottleneck.

Comparing with conventional solutions on CPU, GPU-based algorithm implementations from Fastvideo SDK demonstrate 10-30 times performance speed up retaining the same or even better quality of the output and minimizing the host processor workload.


  • OS Windows-7/8/10, Linux Ubuntu and CentOS, L4T
  • NVIDIA GPUs (Kepler, Maxwell, Pascal, Volta) for mobile, laptop, desktop, server
  • NVIDIA Tegra K1, X1 and X2 mobile GPUs
  • Sample projects for MSVC 2017 and gcc

Custom Image Processing SDK for NVIDIA GPUs

Wide range offering of integration services to connect your software with Fastvideo Image & Video Processing SDK.

To achieve high performance on GPU for specific imaging applications Fastvideo is also developing custom SDKs according to agreed specification.

If you can't find in the details above your image processing pipeline, This e-mail address is being protected from spambots. You need JavaScript enabled to view it to discuss the overall possibility.

You can also have a look at our projects in development.


Inspired? What’s Next?

Fastvideo GPU CUDA processing SDK NVIDIA


This e-mail address is being protected from spambots. You need JavaScript enabled to view it




What is xiLab?
Anything displayed with the reference „xiLab“ or in our xiLab space in our booth refers therefore to technologies and prototypes that are developed and functional, but where XIMEA does not commit on release, timelines or final appearance.
We are keen to learn the markets' reaction to items displayed or exposed under this label.
Call for availability.


About Fastvideo

Fastvideo team consists of experienced and highly dedicated professionals focused on image processing using GPU parallel computations. Our technologies show unmatched performance in image compression and decompression, demosaicing, encoding and decoding of video streams in high speed imaging.

By applying the proven NVIDIA CUDA parallel processing technology, we have managed to achieve an extremely high performance of our algorithms on GPU. Our crown jewels are the fastest JPEG codec and demosaicing software. Thanks to ingenious implementation and optimization, our software runs faster than any analogs, and execution on the GPU makes CPU available for other tasks while providing an exhilarating boost in processing speed. More on Fastvideo


XIMEA News - Technology news

Follow XIMEA on


YouTube XIMEA              facebook XIMEA



Instagram XIMEA              twitter XIMEA



                   linkedin XIMEA


Build your Embedded application

Check our concept for Multi-camera aggregation 


Embedded Vision system camera USB3 fast small multiple


Contact us about your Embedded Vision needs!