Powered by our Raven AI Engine, Fluendo AI Plugins offer cross-platform and production-ready solutions optimized for Edge AI that can be used across a wide range of devices and platforms, from desktop PCs to embedded systems.
Easily integrate advanced AI features into existing GStreamer workflows without requiring extensive reconfiguration or disrupting established processes, enabling users to enhance their multimedia content effortlessly.
Run AI solutions efficiently on-device, reducing latency and maximizing resource usage for applications requiring real-time performance in resource-constrained environments like IoT and autonomous systems or offline processing in multimedia applications.
Deploy AI solutions across different hardware environments without worrying about your GPU/CPU/NPU configurations. Our plugins ensure orthogonal and optimal runtime performance in multiple adapters (NVIDIA, AMD, Intel, …)
Easily integrate advanced AI features into existing GStreamer workflows without requiring extensive reconfiguration or disrupting established processes, enabling users to enhance their multimedia content effortlessly.
Run AI solutions efficiently on-device, reducing latency and maximizing resource usage for applications requiring real-time performance in resource-constrained environments like IoT and autonomous systems or offline processing in multimedia applications.
Deploy AI solutions across different hardware environments without worrying about your GPU/CPU/NPU configurations. Our plugins ensure orthogonal and optimal runtime performance in multiple adapters (NVIDIA, AMD, Intel, …)
Each plugin comes pre-configured to handle AI tasks, requiring no AI expertise. The plugins built on Fluendo’s proprietary Raven AI Engine offer seamless integration with GStreamer.
Our system delivers high-performance solutions that work efficiently, even on low-power edge devices. Fluendo AI Plugins empower businesses to transform their video content workflows by improving processing speed, accuracy, and quality across a range of applications.
Each plugin comes pre-configured to handle AI tasks, requiring no AI expertise. The plugins built on Fluendo’s proprietary Raven AI Engine offer seamless integration with GStreamer.
Our system delivers high-performance solutions that work efficiently, even on low-power edge devices. Fluendo AI Plugins empower businesses to transform their video content workflows by improving processing speed, accuracy, and quality across a range of applications.
This plugin enables real-time background subtraction from webcam feeds, seamlessly integrating the resulting video into desktop presentations or virtual environments. It is ideal for video conferencing, live streaming, and content creation.
This plugin enables real-time background subtraction from webcam feeds, seamlessly integrating the resulting video into desktop presentations or virtual environments. It is ideal for video conferencing, live streaming, and content creation.
This plugin applies advanced multi-target detection and tracking algorithms to blur multiple objects, preserving privacy and confidentiality. Particularly valuable for video surveillance, public safety, and video-sharing platforms. Read more about our Anonymizer.
This plugin applies advanced multi-target detection and tracking algorithms to blur multiple objects, preserving privacy and confidentiality. Particularly valuable for video surveillance, public safety, and video-sharing platforms. Read more about our Anonymizer.
This plugin employs a Generative Adversarial Network (GAN) to upscale video and image resolutions by 4x, enhancing the quality of low-resolution content. This is crucial for media restoration, video streaming, and any image clarity applications.
This plugin employs a Generative Adversarial Network (GAN) to upscale video and image resolutions by 4x, enhancing the quality of low-resolution content. This is crucial for media restoration, video streaming, and any image clarity applications.
Our standalone AI plugins are designed to work independently or as part of a larger video processing pipeline, giving you the flexibility to integrate only the features your project requires.
Underwater exploration, inspection, and marine research increasingly depend on underwater drones equipped with high-resolution RGB-D cameras. However, in deep or turbid waters, light absorption and scattering cause significant color distortion—reds and yellows disappear first—reducing visibility for human operators and degrading the performance of …
Enterprises adopting Desktop-as-a-Service (DaaS) solutions to support hybrid or remote workforces often face fragmented corporate branding during employee video conferencing. Because employees connect from virtual desktops and diverse applications, ensuring consistent branded backgrounds across all sessions becomes difficult. This inconsistency …
Businesses are unable to deploy graphically-intensive applications like CAD, medical imaging, or video editing via DaaS to remote workers on consumer-grade internet. Traditionally, supporting these premium use cases requires high-cost infrastructure: dedicated high-bandwidth network connections for each user and powerful, expensive server-side GPUs …
DaaS & VDI administrators currently lack a reliable, non-intrusive way to measure real-time video quality perceived by users. Traditional reference-based metrics (e.g., VMAF, PSNR, SSIM) require an original source stream that is unavailable in most production desktops, making live monitoring impractical. Subjective methods (e.g., MOS following …
Learn how Raven redefines real-time inference with a fully GPU-driven architecture for multimedia and video pipelines.
Table of contents NMS-Raster: Post-processing bounding boxes using the “G” in GPU The bounding box problem Classical NMS NMS-Raster: Z-Aware rasterized suppression Advantages of the approach Implementation Instanced drawing into integer framebuffer Contribution histogram Threshold filtering Strengths of the design Performance NMS-Raster: Post-processing bounding boxes using the “G” in GPU In this article, we explore the challenges of bounding box post-processing in AI-powered object detection and demonstrate how our high-performance inference engine, Raven, addresses them from a novel angle.
Fluendo AI Plugins v1.0.4 provides real-time, AI-powered video anonymization for high-resolution content. Powered by the Raven AI engine, it delivers fast, efficient processing while ensuring privacy compliance.
Our way to ultra-fast AI video processing, Fluendo AI Plugins. Discover more in this article.