IP Library › Granted Patent US 12,614,337
Granted Patent B2
US 12,614,337 · App. 18/490,458 · Granted Apr 28, 2026

System and methods for customizing 3D models

Inventors: Russ Maschmeyer (Berkeley, CA); Eric Andrew Florenzano (San Francisco, CA); Brennan Letkeman (Calgary, CA); Diego Macario Bello (Montreal, CA); Daniel Beauchamp (Toronto, CA)
Assignee: Shopify Inc.
G06T15/04G06T7/11G06T19/20G06T2200/24G06T2219/2021
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,614,337
App. No.
18/490,458
Granted
Apr 28, 2026
Kind
B2
Abstract

A computer-implemented method is disclosed. The method includes: receiving an indication of a first point on a three-dimensional (3D) model; determining a second point in a texture map of the 3D model that corresponds to the first point; performing segmentation of the texture map for identifying portions of the texture map that are related to the second point; and outputting a 3D representation of the identified related portions of the texture map.

Claims (32)

1 . A computer-implemented method, comprising:

receiving input of a selection of a first point on a three-dimensional (3D) model;

determining a second point in a texture map of the 3D model that corresponds to the first point;

identifying portions of the texture map that belong to a same texture or object class as the second point based on performing segmentation of the texture map; and

outputting a 3D representation of the identified portions of the texture map, wherein the 3D representation of the identified related portions of the texture map comprises a 3D version of an image mask.

2 . The method of claim 1 , wherein receiving selection of the first point comprises receiving, via an input device, user input for selecting a point on a render of the 3D model.

3 . The method of claim 1 , wherein the texture map comprises a 2D image representing a projection of the 3D model's surfaces in texture space.

4 . The method of claim 1 , wherein the second point in the texture map is determined based on a mapping of 3D coordinates of the first point to texture space.

5 . The method of claim 1 , further comprising performing a pre-processing segmentation on a render of the 3D model for identifying a minimum cover portion of the 3D model corresponding to the selected first point, wherein the segmentation of the texture map is performed only on the minimum cover portion.

6 . The method of claim 1 , further comprising identifying portions of the texture map that belong to a same surface section as the selected first point in the 3D model.

7 . The method of claim 1 , further comprising receiving a selection of one or more pixel categories, wherein the segmentation of the texture map is performed for identifying portions of the texture map that belong to a same category as the second point for at least one of the selected pixel categories.

8 . A computing system, comprising:

a processor; and

a memory coupled to the processor, the memory storing computer-executable instructions that, when executed by the processor, are to cause the processor to:

receive input of a selection of a first point on a three-dimensional (3D) model;

determine a second point in a texture map of the 3D model that corresponds to the first point;

identify portions of the texture map that belong to a same texture or object class as the second point based on performing segmentation of the texture map; and

output a 3D representation of the identified portions of the texture map, wherein the 3D representation of the identified related portions of the texture map comprises a 3D version of an image mask.

9 . The computing system of claim 8 , wherein receiving selection of the first point comprises receiving, via an input device, user input for selecting a point on a render of the 3D model.

10 . The computing system of claim 8 , wherein the texture map comprises a 2D image representing a projection of the 3D model's surfaces in texture space.

11 . The computing system of claim 8 , wherein the second point in the texture map is determined based on a mapping of 3D coordinates of the first point to texture space.

12 . The computing system of claim 8 , wherein the instructions, when executed, are to further cause the processor to perform a pre-processing segmentation on a render of the 3D model for identifying a minimum cover portion of the 3D model corresponding to the selected first point, wherein the segmentation of the texture map is performed only on the minimum cover portion.

13 . The computing system of claim 8 , wherein the instructions, when executed, further configure the processor to identify portions of the texture map that belong to a same surface section as the selected first point in the 3D model.

14 . The computing system of claim 8 , wherein the instructions, when executed, further configure the processor to receive a selection of one or more pixel categories, wherein the segmentation of the texture map is performed for identifying portions of the texture map that belong to a same category as the second point for at least one of the selected pixel categories.

15 . A non-transitory, computer-readable storage medium storing computer-executable instructions that, when executed by one or more processors, are to cause the one or more processors to:

receive input of a selection of a first point on a three-dimensional (3D) model;

determine a second point in a texture map of the 3D model that corresponds to the first point;

identify portions of the texture map that belong to a same texture or object class as the second point based on performing segmentation of the texture map; and

output a 3D representation of the identified portions of the texture map, wherein the 3D representation of the identified related portions of the texture map comprises a 3D version of an image mask.

16 . The storage medium of claim 15 , wherein receiving selection of the first point comprises receiving, via an input device, user input for selecting a point on a render of the 3D model.

17 . The storage medium of claim 15 , wherein the texture map comprises a 2D image representing a projection of the 3D model's surfaces in texture space.

18 . The storage medium of claim 15 , wherein the second point in the texture map is determined based on a mapping of 3D coordinates of the first point to texture space.

Assignments (5)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 18, 2024
From: SHOPIFY (USA) INC.
To: SHOPIFY INC.
Reel/Frame 066164/0234 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 18, 2024
From: SHOPIFY QUEBEC INC.
To: SHOPIFY INC.
Reel/Frame 066164/0287 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 6, 2023
From: MASCHMEYER, RUSS; FLORENZANO, ERIC ANDREW
To: SHOPIFY (USA) INC.
Reel/Frame 065776/0815 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 6, 2023
From: LETKEMAN, BRENNAN; BEAUCHAMP, DANIEL
To: SHOPIFY INC.
Reel/Frame 065776/0844 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 6, 2023
From: BELLO, DIEGO MACARIO
To: SHOPIFY QUEBEC INC.
Reel/Frame 065776/0865 →
Continuity (2)
Provisional Application 63578211 · Aug 23, 2023
Related Publication 20250069318A1 · Feb 27, 2025
References Cited (4)
US 20230343017A1 · Yang · 2023 [cited by examiner]
CN 108062758B · 2019 [cited by examiner]
CN 116310213A · 2023 [cited by examiner]
Kirillov, Alexander, et al. (“Segment anything.” Proceedings of the IEEE/CVF international conference on computer vision. Apr. 5, 2023). (Year: 2023). [cited by examiner]