cuvilib.comCUVI - GPU Accelerated Imaging Library

Toggle navigation Home Demo Features Download Services Blog Contact IMAGE PROCESSING ON STEROIDS Simple to use, GPU accelerated computer vision SDK CUVI lib - CUDA for Vision and Imaging LIBrary - provides off-the-shelf primitives that add acceleration to imaging applications from medical, industrial and defense domains. Demo Demosaic (DFPD) Blur = 46% Fog Removal Night Vision Rotate = 20° Flip Color Pick (Red) Channel Mix Channel Split Sobel X Sobel Y Luma Sharpen Video Stabilizer Underwater Enhancer Motion Sensor Enhance Underwater Videos & Images. Our underwater enhancer cleans images and videos taken in water by removing unwanted haze and tint. We make it easy to see true colors of the objects in turbid and murky waters. With this, you no longer need to buy expensive hardware for underwater correction or spend hours on photoshop. Take a look at the results in the link below: See underwater-enhancer in action. Realtime Demosaic DFPD Our demosaic based on dfpd (directional filtering with posteriori decision) approach is more robust than the existing solutions and shows no artifacts at high feature areas. Not only the new algorithm removes artifacts, the colors get more natural and the output image is crisp. See demosaic in action. Low-Light Image and Video Enhancement Our low-light filter enhances the low intensity colors in a dark photo taken from a general purpose mobile, CCTV or DSLR camera. Apart from enhancing dark snaps, this feature is also suitable for enhancing your security footage in real-time at dawn, dusk and other low light conditions. See low-light filter in action. Download CUVILib adds acceleration to Imaging applications from Medical, Industrial and Defense domains. It delivers magnitudes better performance than competing solutions. Take a look at the CUVI Features to see the list of GPU accelerated functions which CUVI provides. Powerful yet easy-to-use Exceptional performance: CUVI performs magnitudes faster than Intel® IPP™. It's (very) simple: Intuitive interface. No GPU-programming experience needed. Cross-platform support: Windows, Mac OS and Linux.* Free downloads include Windows OS support for only NVIDIA GPUs. The image/video size limit of free version is 1000x1000 pixels. Enter email to get download links -- You'll be asked to signup for CUVI updates after which you will receive download link for Windows OS. For information on the functionality available with this download, refer to the Wiki page. Consulting FAQs Q: Do you offer both CUDA and OpenCL development? A: Yes, we do. We do try to push you towards CUDA (yes, we're biased) but if you are dead-set on choosing OpenCL, we will use it. Q: Do you have certified engineers? A: NVIDIA is the pioneer in offering GPU developer certification and yes, our engineers are NVIDIA CUDA certified developers. We have equally good OpenCL developers. Q: What kind of hardware setup you have? A: We have all kinds of CPUs and GPUs. From Intel Core2Duo to Intel Core i7 Sandy bridge and from NVIDIA GeForce 9800GT to NVIDIA Tesla C2050, we have single-GPU and multi-GPU workstations for development and testing. Moreover, we're located at 5 minutes walk from a 32-node GPU cluster (128 NVIDIA Tesla C1060) which we can utilize depending upon your requirement. Q: Would you help us choose the right hardware? A: Of course, we would love to! We always recommend the setup (CPU/GPU combination) which we have analyzed to work best for your specific application. The Future is already here with imgServe Smart Image Processing on the Cloud. Your {img}. One {URL} call. Processed on-the-fly. www.imgserve.io We Speed Up Code. We are the go-to guys for anything GPUs because we love what we do. With our deep knowledge and hands-on experience porting and optimizing complex software to GPUs, we speed up any code, not just imaging related. We are the Imaging Experts We are the experts on GPU Accelerated Vision and Imaging. Since 2010, TunaCode has been delivering GPU accelerated solutions to Medical/Defense/Industrial Imaging. -- “ Thanks to the CUVI GPU acceleration library we could add real time 2k and 4k image processing to our film scanning application without writing one single line of GPU code. Previously, we had to use a 12-core Xeon machine. ” -Jean-Pierre Gehrig, EdelTech “ Testimonial ” Name - Company -- Blog -- -- Image Rotation on CUDA with CUVI – Types and Uses Image rotation – which seems trivial – has big implications in computer vision industry. The quality and even more so the speed at which a vision l... -- -- -- CUVI 1.6.0 Available for Download CUVI is a simple to use C++ SDK that provides accelerated image processing and computer vision algorithms. To run CUVI on your machine, you’ll need an ent... -- -- -- CUDA 10.2 is the last release to support macOS Nvidia releases CUDA toolkit version 10.2 on November 20th, 2019 with a bit surprise – it drops macOS support. According to the release notes, 10.2 will b... -- -- -- Debayer comparison: NPP vs CUVI Comparison performed using CUDA toolkit version 9.1 and CUVI release 1.55 on an underlying core i3-6100, GTX 1080 system and benched with NVIDIA Nsight. CUVI an... -- -- Send Contact us for: Off-the-shelf vision solutions GPU based vision prodcut development CUDA/OpenCL kernel optimization GPU porting with CUDA/OpenCL Code performance analysis Copyright ©2010-2020 TunaCode (Limited) Blog | Wiki show-hide-button Send in your query at contact@cuvilib.com and we'll get back to you....