Search Results for "gpu image" - Page 7
Sort By:
Showing 175 open source projects for "gpu image"
View related business solutions-
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
$300 Free Credits for Your Google Cloud ProjectsLaunch your next project with $300 in free Google Cloud credits—no strings attached. Test, build, and deploy without risk. Use your credits across the entire Google Cloud platform to find what works best for your needs. After your credits are used, continue with always-free tier services. Only pay when you're ready to scale. Sign up in minutes and start exploring.
-
1
cphcttoolbox
Cph CT Toolbox is a selection of Computed Tomography tools
Copenhagen Computed Tomography Toolbox is a collection of applications and libraries for flexible and efficient CT reconstruction. The toolbox apps generally take a set of projections (X-ray intensity measurements) and filter and back project them in order to recreate the image or volume that the projections represent. The project includes both mostly informative CPU implementations and highly efficient GPU implementations. Regular releases are hosted at the Python Package Index. -
2
Loaders.css
Delightful, performance-focused pure css loading animations
...Animations are crafted to be smooth and performant, relying on GPU-friendly properties to keep frame rates high even on mobile devices. The set covers common loading metaphors (pulsing dots, rotating squares, bouncing bars), giving designers a consistent visual language across a site while keeping bundle size tiny. -
3
GLIP-LIB
OpenGL Image Processing LIBrary
GLIP-Lib is an OpenGL image processing library written in C++. It features all the necessary tools to quickly build texture filters and pipelines and operate them on the GPU. -
4
reg_stack
For registering stacks of 2D images.
reg_stack is an extension to the open source project, NiftyReg, for the coregistration of a series of 2D images representing a 3D block tissue subjected to histological serial sectioning. The software performs a series of nonlinear image transformations across a kernel of user-specified size to restore data continuity, as the sectioning process results in misalignments and distortions. The NiftyReg package also includes optimizations for parallelization on either the CPU or GPU. reg_stack leverages this feature and extends it to include support for running simultaneous instances of reg_f3d (NiftyReg) on multiple GPUs. -
Enterprise-grade ITSM, for every businessFreshservice is an intuitive, AI-powered platform that helps IT, operations, and business teams deliver exceptional service without the usual complexity. Automate repetitive tasks, resolve issues faster, and provide seamless support across the organization. From managing incidents and assets to driving smarter decisions, Freshservice makes it easy to stay efficient and scale with confidence.
-
5
Ezys
Ezys 3D medical image registration program
Ezys is a non-linear 3D medical image registration program. Ezys fully exploits the parallel computing power of inexpensive commercial graphics processing units (GPU), resulting in a very fast and accurate program capable of running on desktop PCs and even some laptops. On these systems, non-linear image registrations take less than a minute to complete. Ezys implements a diffeomorphic inverse consistent image registration algorithm with a demons-style regularization based on a non-parametric free form deformation model. ... -
6
HIPAcc
Heterogeneous Image Processing Acceleration (HIPACC) Framework
HIPAcc development has moved to github: https://github.com/hipacc HIPAcc allows to design image processing kernels and algorithms in a domain-specific language (DSL). From this high-level description, low-level target code for GPU accelerators is generated using source-to-source translation. As back ends, the framework supports CUDA, OpenCL, and Renderscript. HIPAcc allows programmers to develop imaging applications while providing high productivity, flexibility and portability as well as competitive performance: the same algorithm description serves as basis for targeting different GPU accelerators and low-level languages. -
7
GPU Edge Detector
GPU Interactive Program For Edge detection
This is a standalone, all in one Edge Detector that is mainly running on GPU using the CUDA technology. Each algorithm also has an OpenCV counterpart which is the closest one in terms of speed. This project is partly based on the Sobel Filter sample available as part of the CUDA SDK. This project also partly uses the OpenCV library to load different types of image. This program includes: Prewitt filter, Roberts Cross, Canny edge detector and finally Sobel filter with the ability to modify some variables such as sigma in Canny and see the result in real-time. ... -
8
LBP in multiple platforms
LBP implementation in multiple computing platforms (ARM,GPU, DSP...)
...When selecting a suitable LBP implementation platform, the specific application and its requirements in terms of performance, size, energy efficiency, cost and developing time has to be carefully considered. This is a software toolbox that collects software implementations of the Local Binary Pattern operator in several platforms: - OpenCL for CPU & GPU - OpenCL for GPU (branchless) - C code optimized for ARM - OpenGL ES 2.0 shaders mobile GPUs - C code for TI C64x DSP core (branchless) - C code for TTA processor synthesis If you use the code somewhere, please cite: Bordallo López M., Nieto A., Boutellier J., Hannuksela J., and Silvén O. "Evaluation of real-time LBP computing in multiple architectures," Journal of Real Time Image Processing, 2014 -
9
birgHPCC
Rapid CUDA Cluster Deployment
...While retaining the major functions of the original birgHPC, including automated computing cluster conversion and auto slots detection, the new version (birgHPCC) is capable of creating and configuring a compute unified device architecture (CUDA) computing cluster, hence the extra “C” in the name. In addition to the increase in image size (less than 2 gigabytes) and a new Linux base (previously Debian, now Ubuntu), CUDA-capable bioinformatics software programs, such as NAMD, HOOMD-blue, VMD, GPU-HMMER and GPU-BLAST, are pre-installed in birgHPCC, along with the CUDA driver, libraries and software development kit (SDK). In short, birgHPCC is the world's first CUDA-ready, bioinformatics-based, live DVD. -
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
10
Pixma Frontpanel Library
Library for using Canon Pixma inkjet printer frontpanels
This library makes it possible to reuse the LCD/button frontpanels of Canon Pixma MP620 / MP630 inkjet printers in your own projects. The library makes use of the processing power and RAM that is built into the frontpanels. The library is written for maple / olimexino but might be expanded in the future. Please see the wiki for info on how the display works, the protocol used and how to connect your display to your board: http://sourceforge.net/p/pixmafrontpanel/wiki/Home/ -
11
pngacidbath is the one true PNG image brute force compressor. While other tools simply run down a list of "intelligent" compressor algorithms (some known as zlib methods), pngacidbath tries every byte combination to come up with THE smallest file.
-
12
Renderer for flam3 cosmic recursive fractal flames implemented on GPU. Requires a CUDA-capable graphics card.
-
13
A gathering of state-of-the-art tools for GPU based image processing. They are the sourcecode for related research articles, and provide the basis for own experimentation. All are being implemented forNVidia GPUs in Linux, hence the name "nvision" ;)
-
14
GPUCL is a 100% GPU-based connected component labeling implementation which utilizes the OpenGL API. GPUCL computes bounding boxes of objects and also correctly labels individual pixels in the input image.
-
15
GPUCL is an OpenGL implementation of connected component labeling. All operations are performed fully on the GPU. Every pixel in the source image is correctly labeled with an ID and bounding boxes are computed for each detected blob.
-
16
A fast JPEG2000 encoder running on CUDA-capable GPUs. Supports lossless and lossy encoding. Both commandline tool with GUI and CUDA/C++ library. Visit >> http://cuj2k.sourceforge.net << for further information.
-
17
multiDAC is intended to become a user-friendly tool for image- and videoprocessing in the field of deformation/movement analysis. It is written in C# with some C routines using CPU/GPU parallelization (e.g. CUDA) and features a plugin manager.
-
18
An OS/hardware vendor independent GPU accelerated image and video processing library written in C. Interface allows easy combination and manipulation of customizable filters. Works with an active OpenGL context.
-
19
GLEWpy aims to bring advanced OpenGL extensions to Python. This allows the Python OpenGL developer to use features such as fragment/vertex shaders and image processing on the GPU. It serves as a compliment to PyOpenGL and toolkits such as GLUT and SDL.
-
20
GPUVision is a framework for creating GPU based general purpose programs, image processing programs, and computer vision programs in C++. Supported libraries include matrix operations, graph partitioning, kernels, corner detection, edge detection etc.
-
21
cl-jpeg
JPEG encoder implementation using OpenCL
This is a research project to test GPU (OpenCL) usability for image compression. Jpeg format is chosen because it is relatively simple and I am familiar with it. 2013-01-22: For now only pixel conversion and DCT transform is done with OpenCL, entropy coding is done with CPU in one thread. Unfortunately this implementation is no match for even one threaded SSE2 jpeg encoder, too much data goes through PCIe. -
22
translategemma-4b-it
Lightweight multimodal translation model for 55 languages
...TranslateGemma uses a structured chat template that enforces explicit source and target language codes, ensuring consistent, deterministic behavior and reducing ambiguity in multilingual pipelines. It integrates seamlessly with Hugging Face Transformers through pipelines or direct model initialization, supporting GPU acceleration and scalable deployment. -
23
Ministral 3 3B Base 2512
Small 3B-base multimodal model ideal for custom AI on edge hardware
Ministral 3 3B Base 2512 is the smallest model in the Ministral 3 family, offering a compact yet capable multimodal architecture suited for lightweight AI applications. It combines a 3.4B-parameter language model with a 0.4B vision encoder, enabling both text and image understanding in a tiny footprint. As the base pretrained model, it is not fine-tuned for instructions or reasoning, making it the ideal foundation for custom post-training, domain adaptation, or specialized downstream tasks. The model is fully optimized for edge deployment and can run locally on a single GPU, fitting in 16GB VRAM in BF16 or less than 8GB when quantized. ... -
24
Ministral 3 8B Instruct 2512
Compact 8B multimodal instruct model optimized for edge deployment
Ministral 3 8B Instruct 2512 is a balanced, efficient model in the Ministral 3 family, offering strong multimodal capabilities within a compact footprint. It combines an 8.4B-parameter language model with a 0.4B vision encoder, enabling both text reasoning and image understanding. This FP8 instruct-fine-tuned variant is optimized for chat, instruction following, and structured outputs, making it ideal for daily assistant tasks and lightweight agentic workflows. Designed for edge deployment, the model can run on a wide range of hardware and fits locally on a single 12GB GPU, with the option for even smaller quantized configurations. ... -
25
Ministral 3 14B Instruct 2512
Efficient 14B multimodal instruct model with edge deployment and FP8
Ministral 3 14B Instruct 2512 is the largest model in the Ministral 3 family, delivering frontier performance comparable to much larger systems while remaining optimized for edge-level deployment. It combines a 13.5B-parameter language model with a 0.4B-parameter vision encoder, enabling strong multimodal understanding in both text and image tasks. This FP8 instruct-tuned variant is designed specifically for chat, instruction following, and agentic workflows with robust system-prompt adherence. Despite its size, the model is engineered for practical deployment, capable of running locally on a single 24GB GPU when served in FP8 and even less with further quantization. ...
