# US 2025/0378596 A1 · Generating synthetic images for training machine learning models

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2025/0378596 A1
- Document ID: US20250378596A1
- Status: Published application
- Kind: A1
- Application number: 19/206,766
- Filed: 2025-05-13
- Published: 2025-12-11
- Earliest claimed: 2024-05-15
- Applicants: Robert Bosch GmbH
- Inventors: Kevin Alexander LAUBE; Julio BORGES; Shin-I CHENG
- Web page: https://patentgrep.com/patent/US20250378596A1

## CPC

- G06T 5/70: Denoising; Smoothing
- G06T 11/00: Two-dimensional [2D] image generation
- G06N 20/00: Machine learning
- G06T 5/60: using machine learning, e.g. neural networks
- G06T 5/77: Retouching; Inpainting; Scratch removal
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/30252: Vehicle exterior; Vicinity of vehicle
- G06V 10/774: Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

A method for training a diffusion model, which can be used to iteratively generate a synthetic image from noise in conjunction with a specified conditioning. In the method: a style that the synthetically generated images should have is specified; a set of training images that match the specified style to varying degrees is provided; noise is successively applied to the training images in a specified number of iterations, so that noised versions are created in each case; samples are drawn from the noised versions; the drawn samples are processed by the diffusion model in conjunction with the specified conditioning to produce predictions for the previous noised version in each case; the correspondence between these predictions and the actual noised versions in each case is evaluated by using a specified cost function; and parameters that characterize the behavior of the diffusion model are optimized.

## Claims

### Claim at position 1

1-16. (canceled)

### Claim 17

A method for training a diffusion model, which can be used to iteratively generate a synthetic image from noise in conjunction with a specified conditioning, the synthetic image being consistent with the conditioning, the method comprising the following steps:
specifying a style that the synthetically generated images should have;
providing a set of training images that match the specified style to varying degrees;
successively applying noise to each respective training image of the training images in a specified number of iterations, so that respective noised versions are created;
drawing samples from the respective noised versions;
processing each of the drawn samples by the diffusion model in conjunction with the specified conditioning to produce predictions for a previous noised version in each case;
evaluating a correspondence between the predictions and the noised versions using a specified cost function; and
optimizing parameters that characterize a behavior of the diffusion model with an aim of improving the evaluation that uses the cost function during further processing of training images and samples generated from the training images;
wherein, when drawing the samples, and/or when evaluating the predictions generated from the drawn samples using the cost function, those samples that still reflect the style of the respective training image are represented more strongly, the more closely the respective training image matches the specified style.

### Claim 18 (depends on 17)

The method according to claim 17, wherein:
the set of training images is divided into a correct subset of the training images that match the specified style and a false subset of the training images that do not match the specified style; and
when drawing the samples, and/or when evaluating the predictions generated from samples drawn by using the cost function, those samples that still reflect the style of the respective training image are only taken into account to the extent that they originate from training images from the correct subset.

### Claim 19 (depends on 17)

The method according to claim 17, wherein a threshold value S is defined, up to which samples xt with t≤S still reflect the style of the respective training image.

### Claim 20 (depends on 19)

The method according to claim 19, wherein
for a plurality of candidate threshold values S*, it is tested whether the style of the respective training image x0 can still be unambiguously ascertained from samples xS*, and
a candidate threshold value S* for which it is no longer proves possible for the style of the respective training image x0 to be unambiguously ascertained from samples xS*, is selected as the threshold value S.

### Claim 21 (depends on 17)

The method according to claim 17, wherein the specified style characterizes a transfer function that translates semantic content of an image into the image.

### Claim 22 (depends on 17)

The method according to claim 17, wherein the specified style characterizes a device with which an image was recorded and/or an algorithm with which an image was synthetically generated.

### Claim 23 (depends on 17)

The method according to claim 17, wherein the specified style includes:
an image distortion, and/or
focus blur, and/or
a color scheme and/or a color cast, and/or
one or more textures, and/or
one or more artifacts that occurred during generation of a training image.

### Claim 24 (depends on 17)

The method according to claim 17, wherein
a frequency at which such samples are drawn that still reflect the style of the respective training image, and/or
a frequency at which such samples are drawn that originate from those of the training images with the specified style,
is adjusted so that iteration indices of the total samples drawn are distributed according to a specified distribution.

### Claim 25 (depends on 17)

The method according to claim 17, wherein the specified conditioning includes:
a composition of the training image which consists of objects, and/or
edges of the training image, and/or
other information about the layout of the training image.

### Claim 26 (depends on 17)

The method according to claim 17, wherein the specified conditioning includes a property of the training image, which is to be ascertained by a machine learning model to be trained and for which property prior knowledge is available for monitored training of the machine learning model.

### Claim 27 (depends on 17)

The method according to claim 17, wherein samples of noise from a noise distribution together with a specified conditioning are supplied to the trained diffusion model, so that synthetically generated images are created.

### Claim 28 (depends on 27)

The method according to claim 27, wherein a machine learning model is trained by using the synthetically generated images as training examples.

### Claim 29 (depends on 28)

The method according to claim 28, wherein:
input images recorded with at least one sensor are supplied to the trained machine learning model;
from output subsequently delivered by the machine learning model, a control signal is formed; and
a vehicle, and/or a driver assistance system, and/or a robot, and/or a system for quality control, and/or a system for monitoring regions, and/or a system for medical imaging, is controlled with the control signal.

### Claim 30

A non-transitory machine-readable data carrier on which is stred a computer program including machine-readable instructions for training a diffusion model, which can be used to iteratively generate a synthetic image from noise in conjunction with a specified conditioning, the synthetic image being consistent with the conditioning, the instructions, when executed by one or more computers and/or compute instances, cause the one or more computers and/or compute instances to perform the following steps:
specifying a style that the synthetically generated images should have;
providing a set of training images that match the specified style to varying degrees;
successively applying noise to each respective training image of the training images in a specified number of iterations, so that respective noised versions are created;
drawing samples from the respective noised versions;
processing each of the drawn samples by the diffusion model in conjunction with the specified conditioning to produce predictions for a previous noised version in each case;
evaluating a correspondence between the predictions and the noised versions using a specified cost function; and
optimizing parameters that characterize a behavior of the diffusion model with an aim of improving the evaluation that uses the cost function during further processing of training images and samples generated from the training images;
wherein, when drawing the samples, and/or when evaluating the predictions generated from the drawn samples using the cost function, those samples that still reflect the style of the respective training image are represented more strongly, the more closely the respective training image matches the specified style.

### Claim 31

One or more computers and/or compute instances including a non-transitory machine-readable data carrier on which is stred a computer program including machine-readable instructions for training a diffusion model, which can be used to iteratively generate a synthetic image from noise in conjunction with a specified conditioning, the synthetic image being consistent with the conditioning, the instructions, when executed by the one or more computers and/or compute instances, cause the one or more computers and/or compute instances to perform the following steps:
specifying a style that the synthetically generated images should have;
providing a set of training images that match the specified style to varying degrees;
successively applying noise to each respective training image of the training images in a specified number of iterations, so that respective noised versions are created;
drawing samples from the respective noised versions;
processing each of the drawn samples by the diffusion model in conjunction with the specified conditioning to produce predictions for a previous noised version in each case;
evaluating a correspondence between the predictions and the noised versions using a specified cost function; and
optimizing parameters that characterize a behavior of the diffusion model with an aim of improving the evaluation that uses the cost function during further processing of training images and samples generated from the training images;
wherein, when drawing the samples, and/or when evaluating the predictions generated from the drawn samples using the cost function, those samples that still reflect the style of the respective training image are represented more strongly, the more closely the respective training image matches the specified style.