Detail, an Amsterdam-based startup, has released two apps: Detail Duo and Detail for Mac, that use machine learning and Apple silicon’s Neural Engine to accomplish some amazing tasks on Apple devices. Detail Duo, which is designed for iPhones and iPads, uses both cameras, person segmentation, and speech recognition combined with Apple’s Metal frameworks to allow users to film themselves in the foreground of a vertical video shot with the camera on the backside of an iPhone or iPad. On the other hand, Detail for Mac focuses on multi-camera setups more suitable for a desktop environment and emphasizes multi-cam recording, where camera sources include iPhones, iPads, and webcams. Both apps use the power of machine learning to make video production accessible to all users.
The author of the article, John Voorhees, stumbled upon a story as old as personal computers themselves – every hardware advance that creates a huge amount of performance headroom is eventually consumed by the ever-growing demands of apps. What seemed like more power than average consumers would ever need quickly becomes a necessity as apps like Detail Duo and Detail push that hardware to its limits. Voorhees is impressed by the direction of Apple’s hardware advances when combined with intuitive, well-designed apps like Detail, as they create entirely new opportunities for users.
Regarding the person mentioned in the article, Voorhees wrote that his son Finn is on the team building Detail Duo and Detail, admitting that this could be an influencing factor in his knowledge and following of the apps.
