On the Power of Machine Learning and AI in Digital Graphics Work

Sometimes we’ve got great images to start with. Other times, we need to use some magic! And by magic I mean a combination of the latest technologies and the expertise to know how to use all of it.

Example 1: Restoring a low-res photo from a 2017 social media post

This original image of a field of sunflowers was from a stunning moment in time, but the image file itself was from someone’s 2017 social media post. That means it was small and compressed and lost a ton of detail.

The restored image includes details on the petals, the centers of the sunflowers, reduced noise on the green parts, and an overall more balanced spectrum.

Original Image

original sunflowers
Original image of a beautiful photo of sunflowers in a field.

Restored Image

restored sunflowers
Digitally restored image of a beautiful photo of sunflowers in a field.

Example 2: Restoring an image from a damaged, physical photo

The original image here is of someone’s late father, and is one of only two surviving photos of the man. The original photo is approximately forty years old and all that we had to go on was this digital image of the 40-year-old, damaged photo. (Ideally, we can get a high res scan of a damaged physical photo to start with.)

The cool part of this project was being able to give a daughter some more detail of how her dad may have looked.

Original Image

original damaged photo
Original photo of an unfortunately-damaged portrait of a man; this photo is missing a lot of detail.

Restored Image

restored portrait
Digitally restored portrait of a man. This image has greater detail and clarity, and reflects the end result of a digital restoration project.

Example 3: Face masks in family photos

Here we have someone who needs to wear an N95 mask near other people, and yet just met some family members after a lifetime of not knowing them! So this was a special family portrait to get face-to-face, and here was a way to make it happen safely.

I took this family’s portrait of the group, with Rachael wearing her N95 mask. I also took a reference photo with Rachael’s mask off (while she was by herself). Then, I digitally replaced her masked face with the unmasked one in the family group photo.

This was a personally-satisfying project to pull off.

Actual Image

Cropped in part of a family portrait, showing one person wearing an N95 mask in the group pic.

Created Image

revised pic
Cropped in part of a digitally-remastered family portrait, showing the one person who was wearing an N95 mask in the group pic is now seemingly not wearing a mask.

Example 4: Low resolution photo cropped in a bit too close

Here we have a very joyful photo, cropped in a bit too close. We don’t have either of these people fully in frame due to the close crop.

By expanding the canvas and filling in what was cropped out, the resulting image reveals the two subjects centered in frame, and the background details have been generated. I was also able to balance colors, remove some jpeg artifact, and restore clarity.

Original Image

Miguel original photo
Original photo of a happy man holding a baby; this image is low resolution and cropped in close, not showing the edges of the people.

Generated Image

Miguel revised image
Revised photo of a happy man holding a baby; this image has filled in what was cropped out of the original around the edges of the people, and now they are fully in frame.

Example 5: Photo subject is lacking a detailed context or setting

Here we have a 2023 phone pic that is kinda boring. This is indeed what needs to remain centered, but a context or setting, perspective, and some light adjustments will enhance this image.

In Photoshop, I started with Curves (mostly to white balance – that is a pure white #fff table top), and Exposure. I used basic perspective transform tools. And then I used Generative Fill, which is machine learning based, to create the table’s edge and a setting.

Original Image

simple photo before
Original cell photo pic of multicolored cutouts of hands and hearts laid out on a white table surface.

Enhanced Image

simple photo enhanced
Enhanced image using the cell photo pic of multicolored cutouts of hands and hearts laid out on a white table surface to start, adjusting curves, exposure and perspective, and generating a table edge and background.

Example 6: Photo subject is okay but you want to replace the background

Here we have another old starting image, a 2013, low resolution phone pic. The subject is low resolution but adequate, and the background is a bit distracting.

While I’m not a fan of using AI to create falsehoods, I don’t mind using generative fill to replace backgrounds that are not the purpose of the image. In this case, the “interesting thing” is that there is a person in front of a car, entirely buried by snow. I never recommend touching that.

As much as I enjoy using the tools available today for digital editing when needed, and this blog post includes a sampling of some different use cases of such, I always recommend ensuring that the truth of what you are representing remains through the end.

To enhance this graphic, I ran neural filters to remove jpag artifact. You can see evidence of this in some restored image clarity. I then adjusted exposure in post and used Generative Fill to build a different background to replace the distracting background.

Original Image

BeforePhoto of Rachael and her snowy car
Original low resolution cell phone pic from 2013 showing Rachael standing in front of her little Honda, entirely buried beneath snow. The subject is fine but the background is distracting.

Enhanced Image

After photo of Generative Fill for Rachael and her car
Revised image of Rachael standing in front of her little Honda, entirely buried beneath snow. Starting with the 2013 low res cell phone pic, adjusting exposure, running neural filter to reduce jpeg artifact, and using Generative Fill to replace the distracting background with something more neutral that maintains perspective.

About Erika Sanborne

Erika Sanborne has been producing digital media since 2010, specializing in portraiture for people who hate it but need it, digital graphics restoration of many kinds, accessible explainers and instructional technology (corporate explainers, classroom tech), data visualizations and animation.