Search Results for "gpu"

...Unlike traditional speech translation systems that rely on multi-stage pipelines, Transcoder directly translates one speaker’s video into another language while preserving facial expressions, lip-sync, and vocal identity. Designed for real-time use and production-grade pipelines, Transcoder combines advanced deep learning models with GPU acceleration to deliver high-quality translations across languages. It’s built with researchers and developers in mind, offering tools for testing, evaluating, and deploying AI-driven media localization.

Important: Groimp migrates to Gitlab. You can find the latest code at "https://gitlab.com/grogra/groimp/". The version on Sourceforge will not be updated anymore. The modelling platform GroIMP is designed as an integrated platform which incorporates modelling, visualisation and interaction. It exhibits several features which makes itself suitable for the field of biological or ALife modelling: The “modelling backbone” consists in the language XL. It is fully integrated, e.g., the...

Skija is a high-performance, Java bindings library for the Skia graphics engine, allowing JVM and Kotlin applications to access the full capabilities of Skia’s 2D GPU-accelerated graphics without writing native code. Skia is the same graphics engine used in Chrome, Android, Flutter, and other platforms, and Skija leverages this robust foundation to provide fast rendering of paths, text, images, transformations, filters, and animations within desktop and embedded Java environments. The project focuses on delivering idiomatic Java/Kotlin APIs that map cleanly to Skia primitives, giving developers a powerful tool for building custom graphics, charting, GUIs, games, and visual effects with minimal overhead. ...

blitz-image is a library to support extremely fast image processing in java, harnessing GPU acceleration via OpenCL. Although more features will be added in time, the initial focus is on very fast high-quality image resizing, including bicubic resizing (both upscale and downscale). The performance of a typical bicubic upscale operation is typically in the order of 10 times faster than via the standard AWT mechanism using RenderingHints.VALUE_INTERPOLATION_BICUBIC.

Java implementation of a software renderer. Software rendering is handled only by a CPU, without any GPU support. Renderer is implemented in pure Java, without any additional frameworks. Additional requirements: JDK / JRE 8

Scene is a computer vision framework that performs background subtraction and object tracking, using two traditional algorithms and three more recent algorithms based on neural networks and fuzzy classification rules. For each detected object, Scene sends TUIO messages to one or several client applications. The present release features GPU accelerated versions of all the background subtraction methods and morphological post processing of the object blobs with dilation and erosion filters, implemented in OpenCL. The framework was mainly designed as a toolkit for the rapid development of interactive art projects that explore dynamics of complex environments. The Scene GUI runs and compiles under Windows, Linux, and MacOS X, and is available in both 32 bit and 64 bit versions.

...Using xuggle as video decoder, we are able to read most popular videocodecs. Supports iGuard IP-250E IP/Network Camera. With MJPEG-Stream-Server for multiple clients like VLC. GPU support with OpenCL and jogamp.

proGPUKLT is a library for the Processing programming language and environment that wraps a GPU-implementation of the Kanade-Lucas-Tomasi feature tracker used for computer vision applications.

A graphical toolkit to use the GPU (Graphical Processor) to perform general purpose operations.