Adobe Sneaks Object-Aware Editing Engine and Major New Generative AI Innovations for Photo, Video, Audio and 3D

Adobe Sneaks Object-Aware Editing Engine and Major New Generative AI Innovations for Photo, Video, Audio and 3D
B&T Magazine
Edited by B&T Magazine



At Adobe MAX – the world’s largest creativity conference –Adobe has unveiled Project Stardust, a powerful new object-aware editing engine.

The editing engine uses generative AI to revolutionize image editing, and its latest collection of early-stage innovations, highlighting exciting new uses of generative AI and 3D technologies across multiple creative domains, including photo, video, audio, 3D, design and fashion applications. The 11 inventions are featured in Adobe’s annual “Sneaks” showcase, where Adobe engineers and research scientists offer first looks or “sneak peeks” at prototype ideas and technologies, each showing future potential to become important elements of Adobe products that are trusted by millions of users across the world.

Project Stardust enables users to easily select, edit and even delete complex elements in any image, making image editing more intuitive, accessible and time-efficient for any user.

“Adobe Sneaks are a can’t-miss, fan-favourite 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,” said Gavin Miller, vice president and fellow of Adobe Research. “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.”

This class of Sneaks offer powerful examples of how generative AI can reimagine video, audio, animation and motion graphics workflows, supercharging discovery and ideation processes and cutting post-production time from days to minutes.

Photo

  • Project Stardust is a powerful new object-aware editor that revolutionizes image editing and magically moves or removes objects simply by clicking on them. With Project Stardust, users can easily select, edit and delete complex elements in any image – enabling them to select persons in a photograph, move them to a different place in the composition and fill in the background where they were previously standing. Users can also change elements like the colour of a person’s clothing and the position in which they’re standing – treating any image like a file with layers.
  • Project See Through is an AI-powered tool that makes it simple to remove reflections from photos. Glass reflections are an annoyance that everyone is familiar with in photos, obscuring the subject of the image, and often making it unusable. Though it’s difficult if not impossible to remove reflections using existing software, See Through dramatically simplifies the process.

Video & Audio

  • Project Fast Fill brings the power of Firefly generative AI to video for the first time. Leveraging Generative Fill technology – which Adobe Photoshop already uses to ease the addition, removal, or expansion of content in images with simple Firefly-powered text prompts – Project Fast Fill offers an early look at what human-prompted generative AI could enable inside Adobe video editing tools including Premiere Pro and After Effects.
  • Project Dub Dub Dub automates the video dubbing process, making a historically labour- and cost-intensive process as easy as clicking a button. Thanks to Project Dub Dub Dub’s AI capabilities, a recording or audio track of a video can be automatically translated to all supported languages while preserving the voice of the original speaker, temporally aligned with the original dialogue and ready to publish.
  • Project Scene Change makes it easy for video editors to composite a subject and scene, from two separate videos captured with different camera trajectories, into a scene with synchronized camera motion.
  • Project Res Up is a tool that easily converts video from low- to high-resolution using innovative diffusion-based upsampling technology.

3D & Design

  • Project Poseable represents a breakthrough in AI-based image generation models, making it easy for the image generator to seamlessly interact with large 3D objects, including poses from photos of real people. The prototype is integrated with Project Poseable which can create a 3D rendering from text input, take depth and perspective into consideration, and re-align the object. While creating 3D scenes with traditional skeletal systems is technically complex and time-consuming, Project Poseable offers an effortless alternative that makes it possible for anyone to expand their creative horizons.
  • Project Neo enables creators to incorporate 3D shapes in their 2D designs – all without requiring technical expertise in 3D creation tools. Today, creators of 2D designs such as infographics, posters, or logos are often limited in their ability to incorporate 3D elements given the complexity of those workflows, which can require years of experience. Project Neo enables creators to embrace simplified 3D design within 2D tools and methods.
  • Project Primrose blurs the line between technology and fashion, demonstrating the potential for flexible textile displays – and turning clothes into creative canvases. This interactive dress can offer infinite style possibilities, displaying content created with Adobe Firefly, After Effects, Stock and Illustrator.
  • Project Glyph Ease makes customized lettering more accessible by streamlining the tedious design process of glyphs – the specific design and shape elements of each letter character. Beginning with a hand-drawn letter shape, Project Glyph Ease uses AI to automatically generate an entire set of glyphs matching the input lettering style. Users can then easily edit the generated glyphs in Illustrator.
  • Project Draw & Delight offers a suite of generative AI tools that helps anyone along their creation journey, from transforming initial ideas – often represented as rough doodles or scribbles – into polished and refined sketches, then experimenting with colour palettes, style variations and different backgrounds.

This year’s MAX Sneaks is co-hosted by actor, comedian and singer Adam Devine. Watch the full Sneaks session here and read more about each Sneak on the Adobe blog.




Please login with linkedin to comment

Latest News