Introducing CUDA-based Image Signal Processing (ISP) Library for NVIDIA platforms! CUDA ISP accelerates Image Processing algorithms by offloading their execution to an available NVIDIA GPU, allowing the CPU to handle more critical tasks.
The CUDA ISP core is based on NPP and is GStreamer-ready thanks to GstCUDA. It is also compatible with x86-based systems and NVIDIA Jetson embedded platforms.
With our CUDA ISP library, you can now perform essential image processing tasks such as Bayer binary shifting, debayering, and auto-white balancing on interleaved RGB and I420 planar formats, all with the help of your NVIDIA GPU.
More resources:
RidgeRun’s article on our CUDA ISP Library
Platforms Supported
- NVIDIA Jetson
- x86 platforms with NVIDIA GPUs