Get the newsletter
Adobe · AI / ML · Filed Feb 10, 2025 · USPTO published Aug 13, 2026 · Aug 13 release

Adobe Patents AI Fill That Compares Colors Twice to Reduce Patchy Results

When an AI fills in a missing chunk of a photo, getting the colors right is surprisingly hard. Adobe has filed a patent for a training trick that checks AI-generated fill against the original image twice, in two different color systems, to catch errors that a single check would miss.

AI inpainting tool seamlessly filling missing elements into a beach scene photograph. Drawing from patent filing US 2026/0237025 A1.
AI inpainting tool seamlessly filling missing elements into a beach scene photograph.All 14 drawings ↓
Publication number
US 2026/0237025 A1(US20260237025A1)
Applicant
Adobe Inc.
Filed · Published
Feb 10, 2025 · Aug 13, 2026
Inventors
Haitian Zheng, Jianming Zhang, Jingwan Lu, Sohrab Amirghodsi, Yuqian Zhou, Zhe Lin
Status when we published
Examiner raised objections; the company can respond
Document
20 claims
US classification
345/604
Examiner
GUO, XILIN (Art Unit 2616)

How Adobe teaches its AI to fill gaps in photos more accurately

Every time an AI photo editor fills in a missing or deleted part of an image, it has to guess what belongs there, including shapes, textures, and especially colors. If the AI's training doesn't penalize subtle color errors hard enough, the filled area can look slightly off even when the shapes are fine.

Adobe's patent describes a way to make that training stricter. Instead of grading the AI's work once, the system grades it twice: once in the standard way photos are normally measured, and once after converting both the AI's version and the correct version into a different color space (a different mathematical way of describing color). That second check catches tonal and hue errors that the first pass can miss.

The result is an AI model that, after training, is more sensitive to color accuracy when it fills in parts of a photo. For you as a user, that could mean fewer times when a photo edit looks almost right but has a weird tint or an oddly flat tone in the filled region.

From the filing · CLAIM 1
… generating a first measure of loss based on comparing the modified digital image with a ground truth version of the digital image with the region complete; generating a transformed modified digital image and a transformed ground truth image of the digital image by performing a color space transformation …

Translation: The system checks how well the AI filled a gap by comparing the result to the original image in two different color modes.

How the two-loss color comparison guides the generative model

The patent describes a training pipeline for a generative model (an AI system that can create or complete image content) specifically focused on inpainting, which means filling in a missing or masked region of a photo so it blends with the rest.

During training, the model generates a filled version of a photo. The system then measures how wrong that fill is using two separate calculations:

  • First loss: a standard pixel-by-pixel comparison between the AI's filled image and the correct (ground truth) image, measured in the usual RGB color system.
  • Second loss: both images are converted into a different color space (such as Lab or HSV, which separate brightness from color information in a way RGB doesn't), and the comparison is repeated there. This second color space makes certain hue and luminance errors more visible mathematically.

Both loss values are then combined and used to update the model's parameters (the millions of internal numbers that control how the AI behaves). By penalizing color errors from two angles at once, the training signal is more sensitive to the kinds of color mistakes that a single measurement would underweight.

The approach is purely a training-time change: the deployed model runs normally; only the process used to teach it is different.

From the filing · THE ABSTRACT
From the first measure of loss and the second measure of loss, the disclosed systems modify parameters of a generative model.

Translation: The software uses these two separate color comparisons to automatically adjust and improve how the AI generates images.

What this means for AI photo editing tools like Firefly

For anyone who uses AI-powered photo editing, color accuracy in filled or removed regions is one of the most common reasons an edit looks fake. A sky that's been extended, an object that's been erased, or a background that's been swapped can all fall apart at the color level even when the geometry looks plausible. Adobe's approach targets exactly that failure mode by making the training process more sensitive to color errors without requiring new hardware or a fundamentally different model architecture.

This is a software-only improvement to a training recipe, which means the path from patent to shipped feature is relatively short if the results hold up in testing. Adobe already ships generative fill in Firefly and Photoshop, so the infrastructure to deploy a better-trained inpainting model is already in place. Adobe's color-accuracy work sits alongside a broader wave of new Big Tech patents in generative image training, where companies are competing on training methodology as much as on model size.

Source: US 2026/0237025 A1 at the USPTO (PDF). Full patent text and figures are in the official publication.

Get our take in your Top Stories

Liked this breakdown? Add Patentlyze as a preferred source on Google, and our plain-English take shows up more often in your Top Stories the next time Adobe patent news breaks.

There are more where this came from

We read every patent application Big Tech publishes and send you the ones worth knowing. Plain English, free, every week.

The drawings · 14 sheets

14 drawing sheets from US 2026/0237025 A1 · click any drawing to enlarge

System architecture of editing platform, drawing sheet 1 from US 2026/0237025 A1
Sheet 1 System architecture of editing platform
Dual color space comparison process, drawing sheet 2 from US 2026/0237025 A1
Sheet 2 Dual color space comparison process
Pixel value amplification calculation steps, drawing sheet 3 from US 2026/0237025 A1
Sheet 3 Pixel value amplification calculation steps
Sampling pixel sets for color tuning, drawing sheet 4 from US 2026/0237025 A1
Sheet 4 Sampling pixel sets for color tuning
Applying color tune mapping function, drawing sheet 5 from US 2026/0237025 A1
Sheet 5 Applying color tune mapping function
Loss calculation across color spaces, drawing sheet 6 from US 2026/0237025 A1
Sheet 6 Loss calculation across color spaces
AI inpainting process on coastal image, drawing sheet 7 from US 2026/0237025 A1
Sheet 7 AI inpainting process on coastal image
Image upload interface with prompt box, drawing sheet 8 from US 2026/0237025 A1
Sheet 8 Image upload interface with prompt box
Show the other 6 sheets
Adobe Patents AI Fill That Compares Colors Twice to Reduce Patchy Results patent drawing, sheet 9
Sheet 9
Adobe Patents AI Fill That Compares Colors Twice to Reduce Patchy Results patent drawing, sheet 10
Sheet 10
Adobe Patents AI Fill That Compares Colors Twice to Reduce Patchy Results patent drawing, sheet 11
Sheet 11
Adobe Patents AI Fill That Compares Colors Twice to Reduce Patchy Results patent drawing, sheet 12
Sheet 12
Adobe Patents AI Fill That Compares Colors Twice to Reduce Patchy Results patent drawing, sheet 13
Sheet 13
Adobe Patents AI Fill That Compares Colors Twice to Reduce Patchy Results patent drawing, sheet 14
Sheet 14
Patent filing page

More in AI image & video

All 223 AI image & video patents →

Watchlists this filing belongs to

All watchlists →