Beamr and Intempora to Bring Real-Time ML-Safe Lossless Compression to RTMaps

Beamr and Intempora add real-time ML-Safe lossless and content-adaptive compression options to RTMaps, targeting massive autonomous vehicle video datasets.

Rhea-AI Summary

Beamr Imaging (BMR) and Intempora, a dSPACE company, will demonstrate ML-Safe lossless video compression integrated with RTMaps for autonomous vehicle and ADAS development. The solution compresses 12-bit Bayer camera output in real time on the GPU in the test vehicle’s data logger, reducing video data at the point of capture with zero stated data loss.

Initial Beamr testing on recordings from eight 8-megapixel cameras showed a 47% reduction in file size, nearly doubling per-vehicle capture capacity and accelerating transfers from vehicle to cloud. RTMaps users will have two compression modes across their pipeline: ML-Safe lossless for bit-exact data, and content-adaptive compression that reduces video data load by up to 50% while preserving ML model accuracy. The joint demonstrations will take place at AutoSens Europe in Barcelona, September 22–24 (stand 131), and at the dSPACE User Conference in Santa Clara, California, on September 23.

Market Context

On Sep 16, 2026, Beamr’s related ML-Safe launch was followed by a 0.81% decline; the current RTMaps ...

Analysis

On Sep 16, 2026, Beamr’s related ML-Safe launch was followed by a 0.81% decline; the current RTMaps demonstration continued the same lossless-compression program without reporting a new commercial term.

Key Figures

Lossless reduction: 47% Camera format: 12-bit Bayer Content-adaptive reduction: Up to 50%

Lossless reduction

47%

Recordings from eight 8-megapixel cameras

Camera format

12-bit Bayer

Raw test-vehicle camera output

Content-adaptive reduction

Up to 50%

While preserving ML model accuracy

Historical Context

1 past event · Latest: Sep 16

1 event

1. Sep 16

   ML-Safe launch

   24h Move

   -0.8%

   Launched ML-Safe lossless compression for AV fleets with reported 47% smaller files

24h Move is the share-price change in the day after each event; other market factors may also have contributed.

Key Terms

lossless compression, 12-bit Bayer, gpu, middleware

4 terms

lossless compression technical

"demonstrate Beamr’s ML-Safe lossless compression for RTMaps"

A method of shrinking digital files so they take up less space without losing a single bit of original information; when you unpack the file, it is identical to the original. For investors, lossless compression matters because it preserves the accuracy of financial records, regulatory filings and transaction data while cutting storage, backup and transmission costs—like folding and organizing clothes tightly so you can fit more in a suitcase without leaving anything behind.

12-bit Bayer technical

"Beamr demonstrates lossless compression for 12-bit Bayer"

A 12-bit Bayer is an image sensor output format where each pixel’s raw color value is recorded with 12 bits of precision and color is captured through a Bayer color filter array that arranges red, green and blue filters over the sensor. It matters to investors because higher bit depth and the Bayer arrangement affect a camera system’s detail, color accuracy, and dynamic range—traits that influence product performance, processing requirements, and cost in imaging-related businesses.

gpu technical

"runs in real time on the GPU already in the test vehicle"

A GPU (graphics processing unit) is a specialized computer chip designed to handle many calculations at once, originally for rendering images and video but now widely used for tasks like artificial intelligence, data analysis and high-performance computing. Investors watch GPU demand and prices because strong sales often signal growth for chip makers and their customers, affect profit margins and capital spending, and can forecast wider trends in gaming, AI adoption and cloud services.

middleware technical

"RTMaps is a modular development and execution middleware"

Middleware is software that acts like a bridge or translator between different applications and systems, allowing them to share data and work together smoothly. Investors care because middleware influences how reliably a company’s technology runs, how easily new features or partners can be added, and whether a software provider has steady, repeatable revenue from integration services—factors that affect growth, costs and long‑term value.

AI-generated analysis. How Rhea-AI works. Not financial advice.

See more from StockTitan in Google Search and AI answers. Adds StockTitan as a preferred source · opens Google

Add on Google Not now

Autonomous vehicle and ADAS teams using RTMaps will get two compression modes to apply across their pipeline - lossless and content-adaptive.

Join the demonstration at AutoSens Europe in Barcelona, September 22–24, stand 131; and at dSPACE User Conference, September 23 in Santa Clara, California

Herzliya, Israel, Sept. 22, 2026 (GLOBE NEWSWIRE) -- Beamr Imaging Ltd. (Nasdaq: BMR), a leader in video optimization technology and solutions, and Intempora, a dSPACE company and pioneer in advanced software solutions for autonomous driving, today announced that the companies will demonstrate Beamr’s ML-Safe lossless compression for RTMaps - reducing video data at the point of capture in the test vehicle, in real time, with zero data loss.

The demonstration will be presented at AutoSens Europe, September 22–24 (stand 131), and at the dSPACE User Conference on September 23.

Autonomous vehicle (AV) teams produce massive video datasets. That volume strains every stage of development. It starts at capture in the test vehicle’s data logger, with recordings of tens of terabytes in one shift; grows as data moves to the cloud and data center; and grows again with simulation and training, where teams add synthetic data to what they recorded.

Beamr demonstrates lossless compression for 12-bit Bayer - the test vehicle camera's raw output. Until now, the encoder in the test vehicle did not accept the 12-bit Bayer format, leaving teams to store it as heavy raw files or discard data they may later need. Beamr’s lossless video data compression runs in real time on the GPU already in the test vehicle’s data logger. Initial Beamr testing showed a 47% reduction on recordings from eight 8-megapixel cameras, nearly doubling how much each vehicle can capture - and smaller files move off the vehicle faster, shortening the time it takes to get recordings to the cloud.

ML-Safe lossless compression joins Beamr’s content-adaptive compression, giving RTMaps users two modes to apply across their pipeline. Content-adaptive compression reduces video data load by up to 50% while preserving ML model accuracy, capture more in the vehicle, and move it faster and at lower cost. RTMaps (Real-Time Multisensor Applications) is a modular development and execution middleware, designed to acquire, synchronize, process, record and replay heterogeneous data streams in real-time.

"The volume of sensor and video data our users move through RTMaps, and then store and manage in IVS (Intempora Validation Suite), keeps growing. Coping with this volume is one of the hardest parts of AV development," said Nicolas Du Lac, CEO of Intempora. "Compression is essential to keep that data workable, and together with Beamr we are demonstrating it in two modes - lossy when a smaller file with preserved ML accuracy aligns with their needs, and lossless when the data has to stay bit-exact."

"The volume of high-resolution camera data is one of the biggest challenges our customers face in data logging and data-driven development," said Peter Ngure, Product Manager at dSPACE. “Efficient compression at the point of capture, without compromising data integrity, is an important building block. We welcome Intempora's collaboration with technology partners like Beamr, giving RTMaps users more options to manage their data across the toolchain."

"AV and ADAS teams see value with compression that matches what each development stage needs. Beamr’s ML-Safe solution lets them make this decision with confidence,” said Haggai Barel, Beamr COO. "Teams can already apply lossy content-adaptive compression that reduces data held in the cloud and the datasets that feed simulation and training; and now we are demonstrating lossless compression that keeps data bit-exact where it is captured in the data logger."

Test ML-Safe compression on your own video data or join us at AutoSens Europe in Barcelona, September 22–24 (stand 131), and at the dSPACE User Conference, West Coast in Santa Clara, California, September 23. Visit beamr.com/lossless

About Beamr

Beamr (Nasdaq: BMR) is a world leader in content-adaptive video compression, trusted by top media companies including Netflix and Paramount. Beamr’s perceptual optimization technology (CABR) is backed by 53 patents and a winner of Emmy® Award for Technology and Engineering. The innovative technology reduces video file sizes by up to 50% while preserving quality and enabling AI-powered enhancements.

Beamr powers efficient video workflows across high-growth markets, such as media and entertainment, user-generated content, machine learning, and autonomous vehicles. Its flexible deployment options include on-premises, private or public cloud, with convenient availability for Amazon Web Services (AWS) and Oracle Cloud Infrastructure (OCI) customers.

For more details, please visit www.beamr.com or the investors’ website www.investors.beamr.com and follow us on Linkedin and X.

About Intempora

Founded in 2000, Intempora is a leading software company based in Paris and a pioneer in providing advanced and innovative software tools for developers of robotics, autonomous vehicles and complex real-time systems for over 25 years. Intempora works closely with OEMs and Tier1 all over the world to fit the expectations of the automotive industry. Since 2020, Intempora is a subsidiary company of the dSPACE group. Together we provide a seamless end-to-end development & testing toolchain for autonomous systems. For more information, visit https://intempora.com and follow us on LinkedIn and Youtube.

Forward-Looking Statements

This press release contains “forward-looking statements” that are subject to substantial risks and uncertainties. Forward-looking statements in this communication may include, among other things, statements about Beamr’s strategic and business plans, technology, relationships, objectives and expectations for its business, the impact of trends on and interest in its business, intellectual property or product and its future results, operations and financial performance and condition, including statements relating to Beamr’s plans to demonstrate and expand its lossless and content-adaptive compression technologies; the expected availability, integration, performance and benefits of such technologies within RTMaps and autonomous vehicle and ADAS workflows; the ability of such technologies to reduce data volumes, increase effective storage capacity, accelerate data transfers or lower costs; Beamr’s relationships with Intempora, dSPACE and other technology partners; and Beamr’s ability to expand into new markets and convert its strategy and technological capabilities into commercial opportunities. All statements, other than statements of historical fact, contained in this press release are forward-looking statements. Forward-looking statements contained in this press release may be identified by the use of words such as “anticipate,” “believe,” “contemplate,” “could,” “estimate,” “expect,” “intend,” “seek,” “may,” “might,” “plan,” “potential,” “predict,” “project,” “target,” “aim,” “should,” “will” “would,” or the negative of these words or other similar expressions, although not all forward-looking statements contain these words. Forward-looking statements are based on the Company’s current expectations and are subject to inherent uncertainties, risks and assumptions that are difficult to predict. Further, certain forward-looking statements are based on assumptions as to future events that may not prove to be accurate. For a more detailed description of the risks and uncertainties affecting the Company, reference is made to the Company’s reports filed from time to time with the Securities and Exchange Commission (“SEC”), including, but not limited to, the risks detailed in the Company’s annual report filed with the SEC on February 26, 2026 and in subsequent filings with the SEC. Forward-looking statements contained in this announcement are made as of the date hereof and the Company undertakes no duty to update such information except as required under applicable law.

Investor Contact:

investorrelations@beamr.com

FAQ

AI-generated questions and answers. How Rhea-AI works. Not financial advice.

What is ML-Safe lossless compression in the Beamr–Intempora RTMaps integration?

ML-Safe lossless compression is a mode Beamr is demonstrating for RTMaps that reduces video data in real time at the point of capture in the test vehicle while, in the company’s words, maintaining zero data loss. It is designed so that compressed data remains bit-exact, matching the original camera output used in autonomous vehicle and ADAS development workflows.

How does the new compression handle 12-bit Bayer camera output?

The demonstration applies Beamr’s lossless compression to 12-bit Bayer, which is the raw output from the test vehicle camera. Previously, the encoder in the test vehicle did not accept the 12-bit Bayer format, so teams either stored heavy raw files or discarded data. With this approach, the 12-bit Bayer stream is compressed in real time on the GPU already present in the test vehicle’s data logger.

What compression modes will RTMaps users be able to apply across their pipeline?

RTMaps users will have access to two modes: an ML-Safe lossless mode for situations that require bit-exact data, and a content-adaptive mode that reduces video data load by up to 50% while, as the company states, preserving ML model accuracy. Teams can choose the mode that aligns with the needs of each development stage, such as data logging, storage, simulation, or training.

Where and when will Beamr and Intempora demonstrate the ML-Safe compression for RTMaps?

The demonstration will be presented at AutoSens Europe in Barcelona from September 22–24 at stand 131, and at the dSPACE User Conference, West Coast, in Santa Clara, California, on September 23. The companies invite interested teams to join these events to see the compression in action.

How can teams try ML-Safe compression on their own video data?

Teams are invited to test ML-Safe compression on their own video data by visiting beamr.com/lossless, or by joining the demonstrations at AutoSens Europe and the dSPACE User Conference on the dates and locations described.