Adobe MAX is a creativity conference that began on Oct 10, 2023, and will end after three days on October 12. At this year’s conference, Adobe hinted at a new Object-Aware Editing Engine alongside new Generative AI Innovations for different media formats.
Today, at Adobe MAX revealed Project-stardust – a new object-aware editing engine that uses generative AI to revolutionize image editing. The company also showcased new applications of generative AI, early-stage innovations, and 3D technologies across multiple domains.
The latest 11 innovations were presented in the “Sneaks” showcase by Adobe, where users saw sneak peeks of upcoming technologies. Among these innovations is Project Stardust, where, Adobe provides a user-friendly experience letting users select, edit, and delete unwanted objects from images.
When editing people in a photograph, users can also change the color of the person’s clothing, edit the position they are in, change the background, or even move them to a different place in the composition, and fill in the background where they were previously standing.
Gavin Miller, vice president and a fellow of Adobe Research, elaborated on the company’s advancement mentioning:
“Adobe Sneaks are a can’t-miss, fan-favorite moment at MAX every year, and for good reason – nothing is more inspiring than brilliant employees demonstrating cutting-edge technologies that might power future Adobe products. Our passion for creators is at the heart of each Sneak, and this year’s showcase highlights exciting new ways generative AI and 3D technologies can supercharge creative expression, reimagining what Adobe tools make possible.”
Adobe also shared different Sneaks for different media formats. For example for Photos, it showcased Project Stardust and Project See Through. The latter refers to an AI-powered tool that makes it simple to remove reflections from photos.
For videos, Adobe presented Project Fast Fill, Project Dub Dub Dub, Project Scene Change, and Project Res Up. Under Project Fast Fill, the capabilities of Adobe Firefly extend to video formats for the first time.
Project Fast Fill allows users to use the Generative AI capabilities on videos and shows what human-prompted generative AI would look like as a part of editing tools like Premier Pro and After Effects.
Project Dub Dub Dub automates the video dubbing process and translates the audio track of a video into any of the 18 supported languages while preserving the original speaker’s voice.
Project Scene Change allows consumers to combine the subject and the scene from two videos into one single video. Whereas, Project Res Up converts video from low- to high-resolution using innovative diffusion-based upsampling technology.
As for 3D and Design capabilities, Adobe showcased Projects Poseable, Neo, Primrose, Glyph Ease, and Draw & Delight.
Project Poseable allows image generators to interact with large 3D objects, including pictures of people. Here, the prototype is combined with Project Poseable, which can re-align the object, focus on depth and perspective, and create a 3D rendering from text input.
Project Neo allows creators to include 3D shapes in their 2D designs, and Project Primrose focuses on flexible texture displays by turning clothes into creative canvases. Also, Project Glyph Ease lets users easily customize lettering.
Lastly, Project Draw & Delight helps users turn their doodles and rough ideas into refined sketches, while also, experimenting with color palettes, backgrounds, and style variations.
If you’re interested in reading more about the technology Adobe is working on, you can head over to the Adobe MAX 2023 website and view the live stream or read the Adobe blog.