# US 2026/0087592 A1 · Image Generation Method Based on Brownian Bridge Diffusion Model, Device and Medium

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

- Number: US 2026/0087592 A1
- Document ID: US20260087592A1
- Status: Published application
- Kind: A1
- Application number: 18/963,744
- Filed: 2024-11-28
- Published: 2026-03-26
- Earliest claimed: 2024-09-24
- Assignees: Shenzhen University
- Applicants: Shenzhen University
- Inventors: Yingying Zhu; Qingwang Zhang; Rui Mao
- Web page: https://patentgrep.com/patent/US20260087592A1

## CPC

- G06T 5/50: using two or more images, e.g. averaging or subtraction
- G06T 5/60: using machine learning, e.g. neural networks
- G06T 5/70: Denoising; Smoothing
- G06T 9/00: Image coding (bandwidth or redundancy reduction for static pictures H04N1/41; coding or decoding of static colour picture signals H04N1/64; methods or arrangements for coding, decoding, compressing or decompressing digital video signals H04N19/00)
- G06V 10/44: Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
- G06V 20/13: Satellite images
- G06T 2207/10032: Satellite or aerial image; Remote sensing
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/20221: Image fusion; Image merging
- Y02T 10/40: Engine management systems
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- Y02T: CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION

## Abstract

The present application relates to an image generation method and apparatus based on a Brownian bridge diffusion model, a device and a medium, wherein the method includes: receiving an image combination including a satellite image and a ground panoramic image; extracting shared features of the satellite image and the ground panoramic image; performing a polar coordinate transformation on the satellite image to obtain an initial latent vector of the satellite image and a latent vector of the ground panoramic image; gradually adding noise into the latent vector of the ground panoramic image to obtain a latent vector of the satellite image; gradually removing the noise in the latent vector of the satellite image to generate a target latent vector; and decoding the target latent vector to generate a target ground panoramic image. The efficiency and quality of conversion from the satellite image to the ground panoramic image are improved.

## Claims

### Claim 1

An image generation method based on a Brownian bridge diffusion model, comprising:
receiving a set of image combination, wherein the image combination comprises a satellite image and a ground panoramic image corresponding to the satellite image;
extracting shared features of the satellite image and the ground panoramic image by means of a cross-view image joint encoder;
performing a polar coordinate transformation on the satellite image, and encoding the satellite image subjected to the polar coordinate transformation and the ground panoramic image to a latent space to obtain an initial latent vector of the satellite image and a latent vector of the ground panoramic image;
in the latent space, performing a Brownian bridge forward process based on the initial latent vector of the satellite image and the latent vector of the ground panoramic image to gradually add noise into the latent vector of the ground panoramic image to obtain a latent vector of the satellite image;
performing a Brownian bridge reverse process based on the latent vector of the satellite image and the shared features to gradually remove the noise in the latent vector of the satellite image to generate a target latent vector; and
decoding the target latent vector to generate a target ground panoramic image.

### Claim 2 (depends on 1)

The image generation method based on the Brownian bridge diffusion model of claim 1, wherein the extracting shared features of the satellite image and the ground panoramic image by means of a cross-view image joint encoder comprises:
respectively extracting features of the satellite image and the ground panoramic image to obtain an initial satellite image feature and an initial ground image feature;
respectively performing average pooling on the initial satellite image feature and the initial ground image feature to obtain a basic satellite image feature and a basic ground image feature; and
embedding the basic satellite image feature and the basic ground image feature into shared feature space by means of a pretrained encoder to obtain the shared features.

### Claim 3 (depends on 2)

The image generation method based on the Brownian bridge diffusion model of claim 2, wherein before the embedding the basic satellite image feature and the basic ground image feature into shared feature space by means of a pretrained encoder to obtain the shared features, the method further comprises:
collecting an original satellite image and an original ground panoramic image corresponding to the original satellite image;
adopting a convolutional neural network as an encoder, and performing feature extraction and feature pooling on the original satellite image and the original ground panoramic image based on the encoder to obtain compressed feature vectors; and
taking an InfoNCE loss function as a model loss function, and training the encoder based on the compressed feature vectors by adopting a GPS coordinate sampling way and a dynamic similarity sampling way to obtain the pretrained encoder.

### Claim 4 (depends on 1)

The image generation method based on the Brownian bridge diffusion model of claim 1, wherein the in the latent space, performing a Brownian bridge forward process based on the initial latent vector of the satellite image and the latent vector of the ground panoramic image to gradually add noise into the latent vector of the ground panoramic image to obtain a latent vector of the satellite image comprises:
constructing a mapping path from the latent vector of the ground panoramic image to the initial latent vector of the satellite image in the latent space;
gradually adding noise to the latent vector of the ground panoramic image along the mapping path by means of forward diffusion, and recording the noise as a real noise label; and
when the current latent vector of the ground panoramic image reaches the initial latent vector of the satellite image, stopping adding the noise, and taking the current latent vector of the ground panoramic image as the latent vector of the satellite image.

### Claim 5 (depends on 1)

The image generation method based on the Brownian bridge diffusion model of claim 1, wherein the performing a Brownian bridge reverse process based on the latent vector of the satellite image and the shared features to gradually remove the noise in the latent vector of the satellite image to generate a target latent vector comprises:
constructing a reverse mapping path based on the latent vector of the satellite image;
gradually removing the noise in the latent vector of the satellite image based on the reverse mapping path, and in each step of a process of removing the noise in the latent vector of the satellite image, updating the current latent vector of the satellite image in conjunction with an attention mechanism and the shared features; and
when performing the reverse mapping path is completed, generating the target latent vector.

### Claim 6 (depends on 5)

The image generation method based on the Brownian bridge diffusion model of claim 5, wherein the gradually removing the noise in the latent vector of the satellite image based on the reverse mapping path, and in each step of a process of removing the noise in the latent vector of the satellite image, updating the current latent vector of the satellite image in conjunction with an attention mechanism and the shared features comprises:
gradually removing the noise in the latent vector of the satellite image based on the reverse mapping path;
in each step of the process of removing the noise in the latent vector of the satellite image, taking the current latent vector of the satellite image as a query vector, and respectively taking the shared features as a key vector and a value vector; and
computing attention weights of the query vector and the key vector, and updating the value vector based on the attention weight to obtain an updated latent vector.

### Claim 7 (depends on 6)

The image generation method based on the Brownian bridge diffusion model of claim 6, wherein the computing attention weights of the query vector and the key vector, and updating the value vector based on the attention weights to obtain an updated latent vector comprises:
computing the attention weights of the query vector and the key vector by adopting a scaled dot-product attention computation way; and
performing weighted summation on the value vector by means of the attention weight to obtain the updated latent vector.

### Claim 8 (depends on 1)

A computer device, comprising a memory and a processor, wherein the memory has a computer program stored thereon, and the processor, when executing the computer program, implements the image generation method based on the Brownian bridge diffusion model of claim 1.

### Claim 9 (depends on 2)

A computer device, comprising a memory and a processor, wherein the memory has a computer program stored thereon, and the processor, when executing the computer program, implements the image generation method based on the Brownian bridge diffusion model of claim 2.

### Claim 10 (depends on 3)

A computer device, comprising a memory and a processor, wherein the memory has a computer program stored thereon, and the processor, when executing the computer program, implements the image generation method based on the Brownian bridge diffusion model of claim 3.

### Claim 11 (depends on 4)

A computer device, comprising a memory and a processor, wherein the memory has a computer program stored thereon, and the processor, when executing the computer program, implements the image generation method based on the Brownian bridge diffusion model of claim 4.

### Claim 12 (depends on 5)

A computer device, comprising a memory and a processor, wherein the memory has a computer program stored thereon, and the processor, when executing the computer program, implements the image generation method based on the Brownian bridge diffusion model of claim 5.

### Claim 13 (depends on 6)

A computer device, comprising a memory and a processor, wherein the memory has a computer program stored thereon, and the processor, when executing the computer program, implements the image generation method based on the Brownian bridge diffusion model of claim 6.

### Claim 14 (depends on 7)

A computer device, comprising a memory and a processor, wherein the memory has a computer program stored thereon, and the processor, when executing the computer program, implements the image generation method based on the Brownian bridge diffusion model of claim 7.

### Claim 15 (depends on 1)

A computer-readable storage medium, wherein the computer-readable storage medium has a computer program stored thereon, and the computer program, when executed by a processor, implements the image generation method based on the Brownian bridge diffusion model of claim 1.

### Claim 16 (depends on 2)

A computer-readable storage medium, wherein the computer-readable storage medium has a computer program stored thereon, and the computer program, when executed by a processor, implements the image generation method based on the Brownian bridge diffusion model of claim 2.

### Claim 17 (depends on 3)

A computer-readable storage medium, wherein the computer-readable storage medium has a computer program stored thereon, and the computer program, when executed by a processor, implements the image generation method based on the Brownian bridge diffusion model of claim 3.

### Claim 18 (depends on 4)

A computer-readable storage medium, wherein the computer-readable storage medium has a computer program stored thereon, and the computer program, when executed by a processor, implements the image generation method based on the Brownian bridge diffusion model of claim 4.

### Claim 19 (depends on 5)

A computer-readable storage medium, wherein the computer-readable storage medium has a computer program stored thereon, and the computer program, when executed by a processor, implements the image generation method based on the Brownian bridge diffusion model of claim 5.

### Claim 20 (depends on 6)

A computer-readable storage medium, wherein the computer-readable storage medium has a computer program stored thereon, and the computer program, when executed by a processor, implements the image generation method based on the Brownian bridge diffusion model of claim 6.
