SANTA CLARA, Calif. — January 5, 2026 — Leads & Copy — Ambarella, Inc. (NASDAQ: AMBA) unveiled its CV7 edge AI vision system-on-chip (SoC) at CES today, optimized for AI perception applications ranging from 8K consumer products to automotive designs.
The CV7 is designed for advanced, AI-based 8K consumer products like action and 360-degree cameras, multi-imager enterprise security cameras, robotics (including aerial drones), industrial automation, and high-performance video conferencing. It also supports multi-stream automotive designs, particularly those using CNNs and transformer-based networks, such as AI vision gateways, fleet video telematics hubs, 360-degree surround-view and video-recording systems, and passive driver assistance systems (ADAS).
According to Fermi Wang, President and CEO of Ambarella, the CV7 allows consumer and enterprise security camera developers to deliver advanced imaging and edge AI performance, improving video analytics and image quality in next-generation products. Wang added that the SoC’s low power consumption, enabled by its 4nm process technology and Ambarella’s AI SoC architecture, reduces thermal-management requirements and extends battery life across AIoT applications. The company has shipped more than 39 million edge AI SoCs to date.
Compared to its predecessor, the CV7 consumes 20% less power, thanks to Samsung’s 4nm process technology. The CV7 is also architected using Ambarella’s algorithm-first design philosophy to efficiently run all processing tasks simultaneously, with extremely high performance and low power consumption.
The CV7 integrates Ambarella’s AI accelerator, image signal processor (ISP), and video encoding, along with Arm® cores and I/Os. Its proprietary, third-generation CVflow® AI accelerator delivers more than 2.5x AI performance over the previous-generation CV5 SoC, supporting CNNs and transformer networks running in tandem.
The CV7 also features industry-leading image signal processing, including high dynamic range (HDR), dewarping for fisheye cameras, and 3D motion-compensated temporal filtering (MCTF). It delivers impressive image quality in low light (down to 0.01 Lux) and improved HDR for vivid details in scenes with contrasting light and dark areas.
The SoC’s hardware-accelerated video encoding (H.264, H.265, MJPEG) doubles encode performance over the CV5, enabling a max video encode of a single 4Kp240 stream, or dual 8Kp30. It can support over 4x 4Kp30 streams concurrently, along with transformer-based AI networks and vision-language models (VLMs).
The CV7’s on-chip general-purpose processing was upgraded to a quad-core Arm Cortex-A73, offering 2x higher CPU performance over the previous SoC. Additionally, its 64-bit DRAM interface provides a significant improvement in available DRAM bandwidth compared to the CV5.
CV7 SoC samples are available now and are being demonstrated at Ambarella’s invitation-only exhibition during CES in Las Vegas this week.
Ambarella’s products are used in video security, advanced driver assistance systems (ADAS), electronic mirrors, telematics, driver/cabin monitoring, autonomous driving, edge infrastructure, drones and other robotics applications. The company’s low-power systems-on-chip (SoCs) offer high-resolution video compression, advanced image and radar processing, and deep neural network processing.
Contacts: Molly McCarthy, mmccarthy@ambarella.com, +1 408-400-1466; Louis Gerhardy, lgerhardy@ambarella.com, +1 408-636-2310.
Source: Ambarella
