SAN FRANCISCO, May 19 — Ouster, Inc. (Nasdaq: OUST) (“Ouster” or the “Company”), a leader in sensing and perception for Physical AI, announced today its collaboration with FUJIFILM Corporation to develop the world’s first native color lidar.
Ouster’s new Rev8 OS family of digital lidar sensors are powered by patented L4 Ouster Silicon with embedded Fujifilm color science, resulting in exquisite native color data and hardware-enabled HDR. By integrating color science at the silicon level, Ouster is redefining lidar as a multi-modal sensor that moves beyond simple depth perception to capture the world in megapixel color resolution on par with industrial cameras.
Built on Fujifilm Color Science
Ouster developed its native color sensing in close collaboration with Fujifilm, a global leader in imaging technology and the gold standard in color science. Beginning with the early prototyping phase, Ouster was able to leverage Fujifilm’s extensive catalog of organic color filters, typically reserved for the semiconductor industry. This strategic access enabled the direct integration of premium materials into Ouster’s digital lidar architecture, ensuring high-performance color sensing was baked into the hardware from the earliest stages of development.
Working with Fujifilm’s experts, Ouster optimized spectral performance at the silicon level to solve the complex challenges of lidar-camera fusion. Specialized filters ensure that the system captures high-fidelity color while maintaining the integrity of the active lidar data, resulting in a clean and accurate visual layer for complex perception.
“Color accuracy and consistency are foundational for perception systems,” said Yoshinori Taguchi, Global Business Director, Wave Control MosaicTM 1 at FUJIFILM Electronic Materials Co., Ltd. “We look forward to Fujifilm’s color science contributing to value creation across various fields – including mapping, robotics, and AI applications – through Ouster’s digital lidar architecture.”
|
1 General term referring to a group of functional materials for controlling electromagnetic light waves in a broad range of wavelengths, including photosensitive color materials for manufacturing color filters for image sensors such as CMOS sensors, used in digital cameras and smartphones. WAVE CONTROL MOSAIC is a registered trademark or trademark of FUJIFILM Corporation. |
Perfect Color, Spatial, and Temporal Alignment for Physical AI Systems
Data quality has been a longstanding bottleneck for Physical AI systems with perception stacks that rely on fusing disparate data from cameras and lidar sensors. For the first time, Rev8 unifies color and depth in a single sensor, where data is captured and processed on a single ASIC with shared timing, optics, and calibration. This tight coupling eliminates the drift and misalignment inherent in traditional sensor fusion, delivering consistent colorized point clouds with perfect color, spatial, and temporal alignment. As a result, Rev8 native color sensors can generate the petabytes of rich, 3D color data necessary to build the next generation of Physical AI systems and train new world models.
Simplified Sensor Stacks and Accelerated Deployment
With Rev8 native color lidar, customers can reduce system complexity by consolidating their perception stack. This approach lowers hardware overhead, simplifies mechanical and electrical integration, and removes the need for time-intensive calibration development between cameras and lidar.
Rev8 customers can expect benefits across a range of applications, including:
- Mapping with faster generation of accurate, colorized 3D environments;
- AI model training using spatially aligned color and depth datasets;
- Object recognition with improved segmentation and classification; and
- Robotics with reduced perception drift and more stable long-term operation.
“Our collaboration with Fujifilm enabled us to bridge the gap between 3D sensing and high-fidelity imaging through pure physics. By integrating their legendary color expertise at the silicon level, we’ve created a sensor that captures the world exactly as it is: spatially accurate and chromatically rich,” said Ouster Optical Engineer Martin Millischer. “For the first time, companies can leverage the foundational depth and color data needed to build the next generation of Physical AI systems.”