Adobe MAX 2021 sneaks: A peek into what’s next

When millions of people across the world join you for the free and all-virtual Adobe MAX 2021, which included hundreds of expert sessions inspiring us to create the next coolest thing, it can be tough to stand out from the crowd. But the can’t-miss, fan-favorite MAX Sneaks – where we show off early technology previews of potential features that may or may not get into our products – turned heads.

Saturday Night Live stalwart Kenan Thompson helped unveil the tech alongside our Adobe engineers, and we have all the highlights right here. Spoiler alert: cool sh&^ ahead. If you see something you especially like, let our teams know on the Adobe MAX twitter channel.

(Want to see the full show? Go to max.adobe.com)

Project Morpheus

Ever see a video of yourself and wish you could change that one little thing? Maybe you forgot to shave, or maybe you left your glasses on. Project Morpheus, video editing tech from our labs, may be able to help. Powered by Adobe Sensei, Project Morpheus uses machine learning to automate frame level changes with smooth, consistent results. Project Morpheus is an entirely new way of authoring and editing content, making the need for painstakingly time-consuming, frame-by-frame edits a thing of the past.

Project Stylish Strokes

Fonts can be a great way to convey personality, tone, and creativity, but you can’t really customize them. Fonts are typically stored as outlines, which makes stylizing or animation difficult. And those types of changes require edits to underlying strokes that make up each individual font character, and people don’t have access to those. Project Stylish Strokes could be the answer. It can help automatically recover those strokes, so they can be stylized - and it even works on fonts with unusual character structures and for languages other than English. The potential options for colors, textures, and animations are endless.

Project Artful Frames

There’s no limit to the stories that animation can help tell, but producing an animated epic is a journey all its own. While traditional animation techniques have been refined over the years, it’s still a time-intensive commitment. Project Artful Frames aims to simplify that process. The AI algorithm behind Artful Frames is a combination of neural representation, optimization, and super-resolution, which gives creators a lot of versatility. This method uses live video as a reference to preserve layout and realistic motion, while creating a fully realized stylized animation. Artful Frames can take an example of an artist’s work, emulate their style, and apply it to a video, turning footage into fine art. Sure, Van Gogh wouldn’t go there – but maybe you could…

Project Strike a Pose

Posing for a photo can be awkward. What are you supposed to do with your hands, for example? With Project Strike a Pose any portrait could become picture-perfect. By providing a reference image of a person in a desired pose, Project Strike a Pose uses machine learning to reposition the person in an image into the same stance. Through a unique mix of data and texture mapping, Project Strike a Pose replicates features such as clothing, hair, and skin color to match the source image, while still accounting for factors like depth and lighting. Bye-bye awkward family portraits.

Project Sunshine

Designers often use vector graphics because of their nearly “infinite” resolution and scalability options – they can go really big or really small (including its small file size). Project Sunshine can take vector graphics to the next level, providing automated suggestions for coloring and shading options. The generative model behind Project Sunshine is auto-regressive, meaning it starts by guessing an element of the image (e.g. “the hair should be black”) and then spirals outward from this decision. Because the results are vectorized, it’s then easy to continue editing and refining the color and shading suggestions.

Project Make it Pop

Content creators are always looking for whimsical ways to spice up their pictures, but there’s only so many in-app filters a person can cycle through. Project Make it Pop provides a seamless, easy-to-use way to add a little something extra to images. Powered by Adobe Sensei, Make It Pop identifies parts of an image (background, foreground, body parts, etc.) and converts them to vector shapes. From there a creator can choose from a gallery of looks, stickers, and animations to apply to the image, transforming a picture into pop art.

Project On Point

Sometimes finding the right stock photo can seem like an endless task, especially if you’re looking for a model in just the right pose. Perhaps Project On Point is the answer for improved image search, because it uses posed-based descriptors to find just the right one. These descriptors are interactive, represented as a 2D stick figure layered over the referenced image, and they can be modified or refined to help get to the image you are looking for. The descriptors can also be combined with other search parameters, filtering for images tagged with specific attributes like “man”, “woman”, or “child,” for example. Project On Point wouldn’t just be limited to stock photo databases either. You could search within your own photo album as well, perfect for a recent fashion shoot or portrait session.

Project In-Between

A picture is worth a thousand words… but could it be more? Project In-Between presents a new way to cherish your memories. Let’s say for example you have two images taken moments apart. Project In-Between utilizes the power of Adobe Sensei to generate an animated bridge between the pair of pictures, breathing new life into old photos. And this isn’t just for static images — using a short video clip, Project In-between can produce silky smooth slow-motion footage so you can savor every moment again and again… and again.

Project Shadow Drop

Traditional shadow rendering methods can be tricky, as they can require geometric knowledge and a familiarity with lighting sources. Project Shadow Drop can solve this problem using the 2D position of the light source and the horizon, so you can automatically generate realistic shadows that can be applied to 2D vector art, 2D animations, and even real images. For designers, artists, and animators, this could prove to be a game changer for short turnarounds, eliminating the need for time consuming, granular edits.