Research Initiatives
RDI at Fluendo drives our continuous evolution. We go beyond immediate product development to investigate emerging technologies, explore untapped domains, and foster a company-wide culture of creativity. Our agile, open innovation model empowers internal talent to transform bold ideas into the next-generation of solutions.
We focus on the earliest stages of the product lifecycle, exploring new business models and transforming fresh ideas into concrete product proposals.
We dive deep into complex, emerging fields building a robust internal knowledge base before productizing.
Our Innovation Committee channels ideas from any member of the company to drive innovation in products, processes, and methodologies.
We believe innovation thrives in collaboration. We proudly support and actively contribute back to the Open Source Software (OSS) community.
Our Research Initiatives
A specialized, cost-effective, and energy-efficient encoding solution leveraging LCEVC-based enhancement layer, screen content coding (SCC) tools, content-aware encoding optimization, guided encoder search, and chroma upsampling to a enhanced EUC (End User Computing) UX (User Experience).
The Raven initiative is Fluendo’s strategic research framework designed to navigate and lead the convergence of Multimedia Processing and Edge Artificial Intelligence. By transforming complex video streams into actionable, real-time insights, Raven establishes a robust foundation for next-generation AI SDKs, tailored consultancy services, and scalable hardware-accelerated products.
The Jay initiative researches AI-driven background removal on the endpoint to optimize video conferencing in virtualized environments and reduce server overhead.
Cheetah explores the usage of multi-core parallelization to slash transcoding times and boost resolution without changing the stack. A codec-agnostic meta encoder combines hardware and software resources to multiply encoding speeds, leveraging all machine resources to accelerate VOD encoding and improve live streaming resolutions.
Bits & Bytes
Explore our blog, one byte at a time. Our team unpack our latest news, industry insights and in-depth articles to connect you with the multimedia world.Blog
Read more about our work
Raven AI Engine v0.4.7: From an AI inference engine to a heterogeneous GPU computing platform
broadcasting, video-surveillance, multimedia-edge-ai, gstreamer, fluendo-ai-plugins, anonymizer, ravenRaven v0.4.7 and FAIP v1.2.6 extend GPU-accelerated AI processing to Ubuntu x64 with CUDA, Vulkan, heterogeneous execution, and user-defined shaders.
Guided encoder search optimization for remote desktop streaming
daas-vdi, codecs, gstreamer, optimization, the-lab, open-source, remote-desktop-coding-tools, h266-vvc, lynxWe explored how operating-system dynamic region information can guide encoder search decisions, reducing unnecessary analysis for remote desktop streaming while preserving coding efficiency.
Screen Content Coding Tools for Remote Desktop Streaming
daas-vdi, codecs, ffmpeg, optimization, the-lab, open-source, remote-desktop-coding-tools, lynxWe used SVT-AV1 as an experimental vehicle to isolate Screen Content Coding tools and evaluate a codec-agnostic methodology for improving desktop streaming quality and efficiency in DaaS & VDI environments.
Benchmarking Remote Desktop Coding Tools for DaaS & VDI
daas-vdi, codecs, gstreamer, optimization, the-lab, remote-desktop-coding-tools, lynxWe used an automated benchmarking workflow to evaluate Fluendo’s Remote Desktop Coding Tools against common codec references for screen-content streaming, measuring compression efficiency, CPU cost, frame delay, and desktop-content suitability.