Impact on Products

The breakthrough research behind Adobe Substance 3D Viewer’s new Text to 3D feature

Creating digital 3D models has always been challenging. But now, the Adobe Research team has developed new technology that makes creating in 3D as easy as in 2D. This groundbreaking technology turns text prompts into 3D models in seconds! Check out the story to learn more.

Read More…

A Papier-Mâché Approach to Learning 3D Surface Generation

Computers have made significant progress in understanding what is depicted in images. How about for 3D? We live in a 3D world. This research project presents a novel approach for generating 3D polygonal meshes.

The Dataset that Made the Cover

Qingnan Zhou, a research engineer at Adobe Research, and a collaborator created a huge poster-style, full-color image showing the objects from their 3D dataset. Now, they are thrilled that their work is being featured on the cover of the journal Computer Graphics Forum.

An AI that Sees the Future

Predicting movement or objects in the next frames of a video feed could potentially save lives or simply increase accuracy across many tasks.

Leveraging Deep Learning to Fix Images

Deep Fill makes editing a photo easier using a form of deep learning known as Generative Adversarial Networks (GANs) to train an innovative system. The tool enables users to remove undesirable objects from an image by letting Deep Fill do the work.

Whose Likes Matter Most? Ask this Learning Algorithm

Now, new work from Adobe Research offers a promising means to empower computers to find online influencers on their own—using sophisticated methods in machine learning.

Search for Great Moments in Videos with Natural Language

We all have long, mostly dull home videos in our memory cards that contain just a few great moments. What if we could train computers to find specific scenes?

Impact on Products

Inside Halide, the open source language engineers use to make imaging tools faster

 Read More…

Stitch Together a Perfect Scene with Experimental Tool

Scene Stitch gives creatives the chance to re-imagine an image and to easily explore a range of possibilities to change it.

Add Depth to VR Video with Sidewinder

Is there a low-cost, easy-capture way to improve the realism of VR video? Adobe Research has found a promising path with Sidewinder.

Cloak: Remove Unwanted Objects in Video

By Meredith Alexander Kunz, Adobe Research Project Cloak, an experimental tool by Adobe Research, offers an innovative way to remove unwanted objects from a video. Object removal is a huge pain point for visual effects artists, who currently spend countless hours manually erasing boom-microphones, special effect wires, distracting objects, and...