3D reconstruction of large models: construction methods, controllers, systems, media, and products.

By employing mesh rasterization and explicit network optimization, the problems of consistency and resource consumption in large 3D reconstruction models were solved, improving the accuracy and quality of the models, especially demonstrating excellent performance in local detail restoration and robustness.

CN119722980BActive Publication Date: 2025-12-02GUANGZHOU HKUST FOK YING TUNG RES INST +1
2 Cites 0 Cited by

Patent Information

Application Number
CN202411598255.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-11-08
Publication Date
2025-12-02
Estimated Expiration
2044-11-08

AI Technical Summary

Technical Problem

Existing technologies suffer from inconsistency issues, high resource consumption, poor local detail, and sensitivity to complex appearances of input images in the construction of large 3D reconstruction models, resulting in low accuracy and quality of the reconstructed models.

Method used

By acquiring training images and performing mesh rasterization rendering to obtain photometric stereo images, these images are input into an explicit network for 3D representation. Loss calculations are performed by combining multiple rendered images and albedo maps, and the explicit network is optimized to construct a large 3D reconstruction model.

Benefits of technology

It improves the accuracy and quality of large 3D reconstruction models, and enhances the model's robustness to the appearance of input images and its ability to restore local details.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

This application proposes a method, controller, system, medium, and product for constructing a large-scale 3D reconstruction model. The method includes: acquiring training images; rendering the training images based on mesh rasterization to obtain a photometric stereo image; inputting the photometric stereo image into a preset explicit network to obtain a three-dimensional representation of the photometric stereo image; rendering the three-dimensional representation to obtain various rendered images, and predicting the albedo of the three-dimensional representation to obtain an albedo map; calculating the loss based on various rendered images, the albedo map, and the photometric stereo image using a preset loss function to obtain a loss value; and optimizing the explicit network based on the loss value to obtain a constructed large-scale 3D reconstruction model. Therefore, this application calculates the loss using various rendered images, the albedo map, and the photometric stereo image, and then optimizes the explicit network based on the loss value to obtain a constructed large-scale 3D reconstruction model, thereby improving the accuracy and quality of the 3D reconstruction model construction.
Need to check novelty before this filing date? Find Prior Art