Jetson Xavier SDK for Image and Video Processing on GPU

Updated: August 27, 2026

Fastvideo Jetson Xavier SDK is our GPU image & video processing pipeline ported to NVIDIA Jetson AGX Xavier: a full ISP from RAW acquisition to JPEG and JPEG2000 output, running on the Xavier Volta GPU for real-time embedded imaging. It brings the desktop SDK's demosaicing, denoising, color processing, and codecs to the CUDA and Tensor cores of the Xavier module.

How these numbers were measured. Fastvideo benchmarks are measured on NVIDIA GPUs, timing pure GPU processing at the resolution, bit depth, format and quality stated on this page. See the full benchmark methodology and test environment and the Fastvideo SDK benchmark report (PDF). Our tools are open source on GitHub and built on NVIDIA CUDA.

Check a single module. Every module in the Fastvideo SDK comes with a command-line sample. Run it on your own images on your own GPU and compare the result with the figures published here.

Check the whole pipeline. A module in the middle of a pipeline cannot be judged on its own: its input is hard to prepare, and its output is an intermediate product you cannot look at. What matters is how it changes the final image and the total time of the schema. Two of our applications run the complete pipeline and report the time of every stage — FastVCR (live cameras or RAW files from disk, so no camera is required) and Fast CinemaDNG (DNG, offline). The benchmark module is included in the free builds of both.

Detailed benchmark data. Measured results are published on our benchmark pages: Jetson / Xavier benchmarks, all benchmarks.

Choosing a Jetson generation? This page covers NVIDIA Jetson AGX Xavier (Volta). Current head module: Jetson Orin ISP SDK. Earlier modules: Jetson TX2 (Tegra X2), Jetson TX1 (Tegra X1), Jetson TK1 (Tegra K1).

That high performance SDK for image and video processing on GPU is a set of separate components which correspond to standard image processing pipeline for camera applications. Jetson SDK covers all image processing stages starting from camera raw image acquisition to JPEG and JPEG2000 compression with storage to RAM or HDD. All image processing is fully done on GPU and this leads to exceptionally high performance. That SDK is also compatible with Jetson Nano, TX1 and TX2.

We wrote these algorithms ourselves

Image processing has always been a trade-off between quality and speed. The methods that give a good result take minutes per frame; the fast ones leave halos and artifacts. The reason is the compute budget: on a CPU there was never enough of it, so algorithms were simplified — and much of the industry still runs on simplifications accepted decades ago.

Fastvideo’s codecs and ISP modules are neither ports of that legacy nor wrappers around third-party code. We designed — and in many cases invented — the algorithms behind our demosaicing, denoising, tone mapping and JPEG/JPEG2000 codecs, and wrote them for CUDA from the start, on top of image-processing expertise built since 2009. An algorithm moved to the GPU still carries the compromises it was simplified for; ours were never made under that constraint. On a modern GPU the budget is large enough that, for practical workloads, the choice between quality and speed no longer has to be made.

That is why you get a complete, tuned imaging solution rather than a bag of GPU primitives — and why, when your pipeline needs something specific, we can change the algorithm itself, not just call it.

Jetson SDK Features

What does the Fastvideo Jetson SDK provide?

Image acquisition from a camera, CPU RAM or GPU memory
Dark frame subtraction (FPN)
Flat-Field Correction (Shading Correction)
White Balance
Exposure correction
Raw Bayer Curves and Levels (master and RGB)
Raw Denoiser (wavelets and/or median filter)
Debayer HQLI, DFPD, MG algorithms
Denoiser for luma and chroma (wavelets, bilateral, NLM)
Color Correction with matrix profile
Color Transforms: RGB->YCbCr, YCbCr->RGB, RGB->HSV, HSV->RGB, etc.
Tone mapping at RGB or HSV with 1D LUTs
3D LUTs for RGB and HSV
RGB Histogram and Parade (waveform monitor)
Crop
Rotation to 90/180/270 degrees and flip/flop
Resize (downscale or upscale)
Remap (rotation to arbitrary angle, affine transform, perspective transform, projection, arbitrary mapping)
Gamma (composite or per-color component)
Sharpening (USM)
Real-time output via OpenGL
JPEG codec (8/12 bits per channel)
Raw Bayer codec for lossy encoding and decoding (8/12 bits per channel)
JPEG2000 codec (8-16 bits per channel)
Trace
Multiplexor
Stream-per-thread support for better performance

Benchmarks for Fastvideo SDK on Jetson Nano, TK1, TX1, TX2, AGX Xavier

About the author

Fyodor Serzhenko, PhD, is the founder and CEO of Fastvideo. He earned his PhD at the Moscow Institute of Physics and Technology (MIPT) in 1993. Since 2009 he has led the development of Fastvideo’s GPU-accelerated image codecs and ISP modules, including the Fastvideo SDK. Connect on LinkedIn.

Why you can trust these results

Fastvideo has built GPU-accelerated image processing software since 2009. Our codecs comply with the standards they implement — JPEG (ITU-T T.81 / ISO IEC 10918) and JPEG2000 (ITU-T T.800 / ISO IEC 15444) — and our tools are open source on GitHub. Every performance figure we publish is reproducible: see our benchmark methodology, download the Fastvideo SDK benchmark report (PDF), and measure it on your own GPU.