Systems and methods for face asset creation and models from one or more images
US-2024119671-A1 · Apr 11, 2024 · US
Method, apparatus, and storage medium for three-dimensional reconstruction of buildings based on missing point cloud data
US12567208B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-12567208-B2 |
| Application number | US-202418423263-A |
| Country | US |
| Kind code | B2 |
| Filing date | Jan 25, 2024 |
| Priority date | Jan 31, 2023 |
| Publication date | Mar 3, 2026 |
| Grant date | Mar 3, 2026 |
How to read this patent
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
- Title
What the patent document calls the invention.
- Abstract
A short plain-language summary of the technical disclosure.
- Assignees and inventors
Who owns or filed the patent and who is credited as inventor.
- Key dates
Filing, priority, publication, and grant dates set the timeline.
- First independent claim
The legal scope of protection — read this for what is actually claimed.
- CPC / IPC classifications
Technology tags used to group this patent with similar filings.
- Citations and related patents
Prior art links and similar publications in this corpus.
Abstract
Official abstract text for this publication.
The invention provides a method, apparatus, and storage medium for reconstructing three-dimensional models of buildings based on missing point cloud data. The method includes integrating image-based point cloud generation, neural network techniques, and skeleton line extraction methods, offering a novel approach to handling missing point cloud data. The generation of point cloud data is achieved using principles of Structure from Motion based on video or panoramic image data. The point cloud is sampled and segmented using a region growing algorithm. A neural network based on PointNet is constructed, utilizing cross-entropy loss functions to assess the missing points in the point cloud. For mapping high-confidence point clouds from sampled points, Truth Points is employed to complete the entire process of real-world three-dimensional reconstruction. The integration of images into the three-dimensional scene is achieved with strict geometric relationships.
First claim
Opening claim text (preview).
What is claimed is: 1 . A method for three-dimensional reconstruction of buildings based on missing point cloud data, comprising the following steps: S1.1. acquiring 360-degree panoramic data of the building and preprocessing it to obtain a sequence of multi-view images; S1.2. matching and reconstructing the sequence of multi-view images to generate a three-dimensional sparse point cloud; S1.3. segmenting the three-dimensional sparse point cloud, applying an encoding-decoding neural network to assess the point cloud's missing data in each segment, and completing the missing point cloud for each segment based on the assessment results to reconstruct the three-dimensional model; S5.1. employing an equal-rectangular projection spherical panorama model during the multi-view projection correction of the 360-degree panoramic images; and S5.2. converting the original input 360-degree panoramic images to three-dimensional panoramic spherical space, with the formula: { x pano q = w · θ q / 2 π + ( w / 2 - 1 ) y pano q = ( h / 2 - 1 ) - h · ϕ q / π , ( - π < θ ≤ π , - π / 2 < ϕ ≤ π / 2 ) { θ q = ( 2 π · x pano q + 2 π ) / w - π ϕ q = π / 2 - ( π - 2 π · y pano q ) / 2 h , ( 0 ≤ x pano q < w , 0 ≤ y
Assignees
Inventors
Classifications
Particle system, point based geometry or rendering · CPC title
Camera pose · CPC title
Infrastructure · CPC title
Artificial neural networks [ANN] · CPC title
Range image; Depth image; 3D point clouds · CPC title
Patent family
Related publications grouped by family.
External sources
Frequently asked questions
Answers are generated from the same data shown on this page.
- What does patent US12567208B2 cover?
- The invention provides a method, apparatus, and storage medium for reconstructing three-dimensional models of buildings based on missing point cloud data. The method includes integrating image-based point cloud generation, neural network techniques, and skeleton line extraction methods, offering a novel approach to handling missing point cloud data. The generation of point cloud data is achieve…
- Who is the assignee on this patent?
- Univ Wuhan
- What technology area does this patent fall under?
- Primary CPC classification G06T17/20. Mapped technology areas include Physics.
- When was this patent published?
- Publication date Tue Mar 03 2026 00:00:00 GMT+0000 (Coordinated Universal Time) (B2). Legal status and post-grant events are not shown on this page.
- What related patents are in patentsdb?
- We list 5 related publications on this page (citations in our corpus or others sharing the same primary CPC).