.png)
Helm.ai, a leading provider of advanced AI software for high-end ADAS, autonomous driving, and robotics automation, today unveiled GenSim-2, its next-generation generative AI model for creating and modifying video data for autonomous driving. GenSim-2 introduces state-of-the-art, AI-based video editing capabilities, including dynamic weather and illumination adjustments, object appearance modifications, and consistent multi-camera support. These advancements provide automakers with a scalable, cost-effective solution to enrich datasets and address the long tail of corner cases in autonomous driving development and validation.
Trained using Helm.ai’s proprietary Deep Teaching™ methodology and cutting-edge generative deep neural networks, GenSim-2 expands on the capabilities of its predecessor, GenSim-1. The new model enables automakers to generate diverse, highly realistic video data tailored to specific requirements, facilitating the development of robust autonomous driving systems.
With GenSim-2, development teams can seamlessly modify weather and lighting conditions such as rain, fog, snow, glare, and time of day (day, night) in video data. The model supports both augmented reality modifications of real-world video footage and the creation of fully AI-generated video scenes. Additionally, it enables customization and adjustments of object appearances, such as road surfaces (e.g., paved, cracked, or wet) to vehicles (type and color), pedestrians, buildings, vegetation, and other road objects such as guardrails. These transformations can be applied consistently across multi-camera perspectives, ensuring realism and self-consistency throughout the dataset.
GenSim-2 addresses critical industry challenges by offering an efficient alternative to resource-intensive traditional data collection methods. Its ability to generate and modify realistic, scenario-specific video data supports a wide range of applications in autonomous driving, from developing and validating software across diverse geographies to resolving rare and challenging corner cases.
“The ability to manipulate video data at this level of control and realism marks a leap forward in generative AI based simulation technology,” said Vladislav Voroninski, Helm.ai’s CEO and founder. “GenSim-2 equips automakers with unparalleled tools for generating high fidelity labeled data for training and validation, bridging the gap between simulation and real-world conditions to accelerate development timelines and reduce costs. These new technology capabilities exemplify our commitment to innovation in AI-based simulation toward autonomous driving development.”
