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

Adobe Patents an AI That Cuts Out Photo Objects at Multiple Detail Levels at Once

Click once on a car in a photo and Adobe's system could instantly offer you the whole car, just the door, or just the door handle, all at the same time, without clicking again.

A smartphone interface demonstrating the selection of a car wheel to generate multiple cutout options at different detail levels. Drawing from patent filing US 2026/0237206 A1.
A smartphone interface demonstrating the selection of a car wheel to generate multiple cutout options at different detail levels.All 12 drawings ↓
Publication number
US 2026/0237206 A1(US20260237206A1)
Applicant
Adobe Inc.
Filed · Published
Feb 13, 2025 · Aug 13, 2026
Inventors
Brian Price, Joshua Myers-Dean, Yifei Fan, Kangning Liu, Jason Wen Yong Kuen
Status when we published
Waiting for an examiner
Document
20 claims
US classification
382/103

What Adobe's layered object-selection AI actually does

Ever tried to select just the right piece of an object in a photo editor, only to keep clicking until you got it? Most selection tools force you to commit: you either grab the whole thing or you painstakingly trace a smaller part.

Adobe's new patent describes an AI that, when you click on an object in an image, figures out the selection at multiple levels of detail simultaneously. Click on a jacket and the system can hand you a selection of the entire jacket and just the sleeve, in one pass. You pick which level of detail fits what you need.

The idea is to stop forcing you to re-click or adjust slider settings just to move between a broad and a tight selection. The AI does the hierarchy work behind the scenes, so your workflow moves faster and with fewer frustrated undos.

From the filing · CLAIM 1
… determining, using a segmentation neural network and based on the user input, a parent token corresponding to a first semantic level for the object and a child token corresponding to a second semantic level for the object that is hierarchically lower than the first semantic level …

Translation: The AI identifies the object at different levels of detail, such as selecting a whole person and then just their hand.

How the neural network builds parent and child mask tokens

The system takes a digital image and a user's click (or set of clicks) on a pixel inside an object. A segmentation neural network (an AI trained to identify and outline distinct regions of an image) then produces two kinds of internal representations called tokens: a "parent token" tied to a broader semantic level (say, the whole bicycle) and a "child token" tied to a narrower semantic level that sits below it in the hierarchy (say, just the front wheel).

  • Parent token: encodes what the object is at a coarser, wider level of meaning
  • Child token: encodes a more granular sub-part, hierarchically nested under the parent

From those tokens, the same neural network generates two separate masks (pixel-level outlines that mark which parts of the image belong to the selection). The first mask corresponds to the parent level; the second to the child level. Both can be displayed to the user at once, letting the person choose which outline to apply.

The key engineering point is that the network is conditioned (trained to respond) on varying semantic levels, meaning it learns to distinguish "whole object" from "part of object" during training rather than running two completely separate models. That single-network approach is what makes generating both masks in one pass feasible.

From the filing · THE ABSTRACT
The present disclosure relates to systems, methods, and non-transitory computer-readable media that generate a hierarchy of masks for a selected object within a digital image.

Translation: Adobe is patenting a way for software to create a layered set of cutouts for any object you click on in a photo.

What this means for designers doing precise photo cutouts

For anyone who edits photos professionally, the most time-consuming part of compositing work is often the selection itself. Cutting a model away from a background is one task; isolating just their collar for a color change is another. Today those are separate operations requiring separate tools, separate clicks, and a lot of patience.

Adobe already ships AI-powered selection tools in Photoshop and Firefly, and this patent points toward a future where a single click hands you a stack of ready-made selections at different granularities. Image editing is one of the more active areas among interesting tech patents right now, and Adobe's hierarchical approach suggests the company is trying to collapse what used to be a multi-step workflow into a single decision point for the user.

Source: US 2026/0237206 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 · 12 sheets

12 drawing sheets from US 2026/0237206 A1 · click any drawing to enlarge

Network architecture for image segmentation, drawing sheet 1 from US 2026/0237206 A1
Sheet 1 Network architecture for image segmentation
Smartphone interface for selecting image cutouts, drawing sheet 2 from US 2026/0237206 A1
Sheet 2 Smartphone interface for selecting image cutouts
Neural network process for generating masks, drawing sheet 3 from US 2026/0237206 A1
Sheet 3 Neural network process for generating masks
Training process for segmentation neural network, drawing sheet 4 from US 2026/0237206 A1
Sheet 4 Training process for segmentation neural network
Training label generation workflow, drawing sheet 5 from US 2026/0237206 A1
Sheet 5 Training label generation workflow
Hierarchy-aware pixel sampling and training, drawing sheet 6 from US 2026/0237206 A1
Sheet 6 Hierarchy-aware pixel sampling and training
Desktop interface displaying multiple cutout options, drawing sheet 7 from US 2026/0237206 A1
Sheet 7 Desktop interface displaying multiple cutout options
Dropdown menu for selecting cutout detail, drawing sheet 8 from US 2026/0237206 A1
Sheet 8 Dropdown menu for selecting cutout detail
Show the other 4 sheets
Adobe Patents an AI That Cuts Out Photo Objects at Multiple Detail Levels at Once patent drawing, sheet 9
Sheet 9
Adobe Patents an AI That Cuts Out Photo Objects at Multiple Detail Levels at Once patent drawing, sheet 10
Sheet 10
Adobe Patents an AI That Cuts Out Photo Objects at Multiple Detail Levels at Once patent drawing, sheet 11
Sheet 11
Adobe Patents an AI That Cuts Out Photo Objects at Multiple Detail Levels at Once patent drawing, sheet 12
Sheet 12
Patent filing page

Watchlists this filing belongs to

All watchlists →