Meet us next:
ICLR
🇦🇹
ISC High Performance
🇩🇪
MLSys
🇺🇸
Meet us next:
🇦🇹
ICLR
All events

Jetraw Core: High-speed, high-ratio RAW image compression for OEMs

Integrate Jetraw Core into your image acquisition or processing pipeline, either as 
FPGA IP Core or
software
Increase your system performance
Improve data management
Future-proof image data for AI/ML
x = Pixel value
y = Pixel occurrence
Compression ratio
From 4:1 to 6:1
Compression speed
FPGA
200Mpx/s/core
Software, per core
200MB/s/core
Data quality
no artifacts
no bias
no filtering

Future-proof your device for data-centric AI

TOP FIT DATA FOR AI

Most images today are processed with AI/ML, where differences in pixel values are critical and may be invisible to the human eye. ML model reliability depends on high-quality data, best achieved with RAW images.
‍
RAW data’s size is a bottleneck for transmission speed, processing, storage and associated costs.

EXISTING SOLUTIONS

Image compression could tackle these, but, currently impose limitations:

Lossy
Lossless
Formats
JPEG2000, JPEG-LS, JPEG-XR
LZF, FLIF, LZ4
Compression ratio
High
Low
Fit for AI in critical applications
No
Yes
Issues
Artifacts in large datasets, compromised outcome validity
Not efficient for AI due to slow transmission speed

WHY RAW FOR AI

Jetraw Core —The first high-ratio image compression with RAW quality control

Jetraw Core is in-camera RAW compression combining the size of lossy formats with the reliability and quality of lossless technologies.

It applies lossless compression to the signal component, following image preparation with lossy compression of the noise. This achieves the highest ratio and the highest quality output on the market.

HOW WE DO IT

Jetraw turns data into measurement by embedding a custom noise model 

based on the sensor’s physical properties. This enables image quality validation and optimization for AI/ML.

Meet Jetraw onboarding team to start your discovery workshop and calculate benefits for your optical system

Enhance your optical systems with advanced and efficient data

5–10x to speed

Get faster data capture, transmission

Higher throughput

Acquire more data even at a lower bandwidth

Battery life

Reduce energy consumption, prolong battery life

Efficient IT infrastructure

Maximize processing and storage capacities

Reliable data

Improve robustness of your AI/ML models

Costs

Reduce data storage expenses while boosting data access speed

Jetraw Core can be integrated as an FPGA IP Core or as a software library

Integration type
FPGA IP Core
Software
High throughput, low latency, power-efficient RAW compression on FPGA
Fast, easily integrated in-camera RAW compression as a software
From 4:1 to 6:1
Indistinguishable from RAW, interoperable
CMOS, sCMOS, CCD camera support
Mono, Bayer and other CFA image sensors support
Tightly-controlled image quality 1.2dB SNR equiv. increase ISO100→ISO115
Image data
  • 16-bit images
  • Configurable image dimensions
RAW image buffer or common file formats
Performance
  • 1 to 32 pixels per clock cycle
  • Up to 200 MHz clock frequency
  • Low latency (~60 clock cycles)
  • Parallel computing of multiple pixels for higher compression throughput
  • 200MB /s/core
  • Multi-threading support
Integration features
  • Backpressure support
  • From 3968 LUT for single core compressor to 70790 for 32 pixels
  • AXI4-stream data interface
  • Available as a software library / codec
  • Callable from C, C++, C#, Java, Python
System support
  • Xilinx FPGAs
  • Intel on request
  • Intel, AMD and ARM CPU support
  • Linux, Windows and Mac support

Address your industry’s challenges with Jetraw Core

Want to learn your benefits? Request a free discovery workshop
Want to learn your benefits? Request a free discovery workshop
Want to learn your benefits? Request a free discovery workshop

“It is extremely appealing for PCO to obtain a compression method that exploits the individual image capture chain of each camera model.”

Gerhard Holst
Head of Science and Research, Excelitas PCO
Integration type
FPGA IP Core
High throughput, low latency, power-efficient raw compression on FPGA
Software
Fast, easily integrated in-camera raw compression as a software
5–10:1 compression ratio
Indistinguishable from raw, interoperable
CMOS, sCMOS, CCD camera support
Mono, Bayer and other CFA image sensors support
No bias, no artifacts, no artificial correlations, no low pass filtering
Tightly-controlled image quality 1.2dB SNR equiv. increase ISO100→ISO115
Image data
  • 16-bit images
  • Configurable image dimensions
Raw image buffer or common file formats
Performance
  • 1 to 32 pixels per clock cycle
  • Up to 200 MHz clock frequency
  • Low latency (~1-line, 2-lines for Bayer)
  • 200MB /s/core
  • Multi-threading support
Integration features
  • Backpressure support
  • This is some text inside of a div block.
  • From 3968 LUT for single core compressor to 70790 for 32 pixels
  • AXI4-stream data interface
  • Available as a software library / codec
  • Callable from C, C++, C#, Java, Python
System support
  • Xilinx FPGAs
  • Intel on request
  • Intel, AMD and ARM CPU support
  • Linux, Windows and Mac support

Take next steps to maximise the value of your image data

FAQ