Three-dimensional scene cross-domain migration method based on neural radiation field representation, computer equipment, readable storage medium and program product

By using a neural radiation field representation method, geometry and coloring modules are trained using multi-view images, and combined with a 2D image transfer network, the consistency of viewpoint style in cross-domain transfer of 3D scenes is achieved, generating images that conform to the style of the target domain.

CN120953492APending Publication Date: 2025-11-14ZHEJIANG UNIV
0 Cites 2 Cited by

Patent Information

Application Number
CN202511042841.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-07-28
Publication Date
2025-11-14

AI Technical Summary

Technical Problem

Existing methods for cross-domain 3D scene transfer struggle to achieve high-quality transfer while maintaining stylistic consistency across different viewpoints.

Method used

By using a neural radiation field representation method, 3D scene reconstruction is performed using real images from multiple perspectives. The geometry module and source domain coloring module are trained to extract content and style features. The target domain coloring module is optimized by combining a pre-trained 2D image cross-domain style transfer network to ensure that the generated images have consistent style under different perspectives.

Benefits of technology

It enables the generation of target domain images with consistent style from the user-specified viewpoint, solving the problem of inconsistent viewpoint style in cross-domain migration of 3D scenes. The generated images conform to the content of the source domain and the style of the target domain.

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

Abstract

The invention relates to a three-dimensional scene cross-domain migration method based on neural radiation field representation, computer equipment, a readable storage medium and a program product. The three-dimensional scene cross-domain migration method comprises the steps that a real image is acquired for three-dimensional scene reconstruction; inputting the three-dimensional scene information into a geometric module to extract content features; inputting the three-dimensional scene information into a source domain coloring module to extract source domain style features; performing volume rendering to obtain a first rendered image, training and optimizing the geometric module and the source domain coloring module until the expectation is met, and freezing the geometric module; inputting the three-dimensional scene information into a target domain coloring module to extract target domain style features; performing volume rendering to obtain a second rendered image; performing style migration on the real image to obtain a stylized image; comparing loss training to optimize a target domain coloring module, and freezing the target domain coloring module until expectation is met; and receiving a specified view angle direction, respectively outputting features by using a geometric module and a target domain coloring module, and obtaining a target domain image through volume rendering.
Need to check novelty before this filing date? Find Prior Art