Odyssey is developing a revolutionary AI system designed to provide creators with unprecedented cinematic world generation capabilities. The company adopts a unique data collection method: staff members carry special camera systems to collect scene data from all over the world. Recently, Odyssey completed an $18 million Series A round of financing, bringing the total financing to $27 million, which will be mainly used to expand its data collection business in California. The editor of Downcodes will explain Odyssey and its breakthrough technology in detail.
An impressive startup is developing a groundbreaking AI system that promises to bring unprecedented cinematic world-generation capabilities to creators. The company called Odyssey uses a unique approach: having staff carry special camera systems on their backs to collect scene data from around the world.
Odyssey, founded by veteran experts in the field of autonomous driving Oliver Cameron and Jeff Hawke, recently completed an $18 million Series A round of financing, led by EQT Ventures, with participation from GV and Air Street Capital. So far, the company’s total financing has reached US$27 million. The funding will be used primarily to expand its data collection operations in California.
The advanced photography system developed by Odyssey weighs approximately 25 pounds and is equipped with six cameras, two lidar sensors and an inertial measurement unit. This system is similar to the Google Street View Trekker, capable of capturing 360-degree panoramic shots at 3.5K resolution while recording depth information metadata with physical accuracy.
The company's core technology lies in feeding collected data into algorithms to capture the detailed features that make up the real world. The process is similar to Meta's Hyperscape project, which enables digital reconstructions of real-life scenes such as forests, caves, trails, beaches, glaciers, parks and buildings. Odyssey has developed multiple generative AI models that can create layers of visual details including object geometry, lighting and motion, and combine them into a single virtual world to create the desired scene.
It is impossible for generative models to create living Hollywood-level worlds without training on large amounts of rich multi-modal real 3D data, the company said in its blog. We believe that an advanced generative world-building model will provide a powerful platform for movies, Content creation such as games has brought revolutionary changes.
While the current world model still has certain limitations, Odyssey plans to expand data collection to other states and countries in the future. Given privacy concerns (the Google Street View team has come under scrutiny from regulators for taking images of public places that violated the privacy of passers-by), the company needs to take appropriate privacy measures as it expands.
The emergence of this technology may completely change the way film and television production and game development are performed, providing creators with more efficient and economical content production solutions. As AI technology continues to advance, we may soon see the application of this revolutionary technology in more fields.
Odyssey's innovative technology has brought new possibilities to industries such as movies and games, and its future development is worth looking forward to. The editor of Downcodes will continue to pay attention to the company's dynamics and bring more relevant reports to readers.