High speed XIMEA xiB cameras with PCIe interface

Updated: August 13, 2026

Fastvideo software processes XIMEA xiB high-speed PCIe cameras on the GPU in real time, handling the large raw data rates these sensors produce. The full ISP and compression run on NVIDIA GPUs, so xiB streams are demosaiced, processed, and recorded live instead of overwhelming the CPU and storage.

Detailed benchmark data. Measured results are published on our benchmark pages: all benchmarks.

Different XIMEA interface or integration? See the xiQ USB3 cameras, the FastVCR application for XIMEA, or the XIMEA CamTool GPU plugin. This page covers xiB high-speed PCIe cameras.

XIMEA high speed xiB cameras are working with CMOSIS, Luxima and Gpixel image sensors (bayer or monochrome) providing an exceptional combination of resolution, speed and image quality. These cameras are connected to PC via PCI-Express interface to allow real time data transfer from camera to system memory. Below you can see some info about image sensors in XIMEA high speed xiB cameras:

CMOSIS image sensors

• CMOSIS CMV12000: 4096×3072, 8-bit, 330 fps

Luxima image sensors

• Luxima LUX13HS: 1280×864, 10-bit, 3675 fps
• Luxima LUX19HS: 1920×1080, 10-bit, 2263 fps
• Luxima LUX160: 4704×3424, 10-bit, 300+ fps

Gpixel image sensors

• Gpixel GMAX0505: 5120×5120, 150 fps @ 10 bit, 40 fps @ 12 bit
• Gpixel GMAX3265: 9344×7000, 10-bit, 71 fps
• Gpixel GSPRINT4502: 2048×1216, 2/3", 8-bit, 3200 fps
• Gpixel GSPRINT4510: 4608×2176, 4/3", 8-bit, 600 fps
• Gpixel GSPRINT4521: 5120×4096, APS-C, 8-bit, 300 fps

Software for real-time image processing on GPU for xiB cameras

How do you process XIMEA xiB PCIe camera data on the GPU?

• Image acquisition
• Frame unpacking for 10-bit and 12-bit modes
• Image linearization
• Dark frame subtraction (FPN)
• Flat-Field Correction (shading correction)
• Bad pixel removal
• White Balance / AWB
• Adaptive Exposure and Gain control
• High quality demosaicing with MG algorithm
• Color correction with matrix profile or DCP profile
• Highlight recovery
• Exposure correction (brightness control)
• Curves and Levels
• Denoising
• Rotation to 90/180/270 degrees and flip/flop
• Crop
• Resize (downscale and upscale)
• Rotation to an arbitrary angle
• Sharpening (local contrast)
• Gamma transform
• JPEG compression and storage on SSD
• Optional conversion to NV12 and h264/h265/av1 video encoding
• Automatic real-time partitioning of AVI/MP4 video files to the specified file size

Compatibility

• CUDA-12.6 for Windows/Linux, NVIDIA GeForce and NVIDIA RTX
• CUDA-11.4 and CUDA-12.2 for NVIDIA Jetson NX, AGX Xavier, Orin
• XIMEA USB3 and PCIe cameras
• Processing of 8-16-bit RAW/PGM/TIFF images from SSD

Benchmarks for GPU ISP

The software can process RAW images from 65 MPix camera (Gpixel GMAX3265 image sensor, 9344×7000, 10-bit, 70 fps) on the NVIDIA GeForce RTX 4090 in real time, the pipeline includes RAW import, RAW-to-RGB transform, color correction, gamma, JPEG encoding, storage to SSD. FastVCR software can process such a data stream without frame drops, and max performance could reach 6 GPix/s or even more with that software.

Software downloads

• FastVCR software for XIMEA cameras on Windows and CUDA-12.6. The software can also work with PGM/RAW/TIFF frames from SSD on Windows.
• FastVCR software for XIMEA cameras on Jetson Nano and CUDA-10.2
• FastVCR software for XIMEA cameras on Jetson NX/AGX Xavier and Orin on CUDA-11.4
• PDF manual for FasVCR software
• XIMEA SDK for Windows/Linux/ARM

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.