Monocular dressing human body reconstruction method for perspective distortion image

Through virtual camera perspective transformation and multi-scale attention enhancement network, combined with pseudo-multi-view feature fusion, the problem of human body reconstruction in perspective distorted images is solved, and high-precision clothing body reconstruction is achieved.

CN120510299APending Publication Date: 2025-08-19TIANJIN UNIV
0 Cites 1 Cited by

Patent Information

Application Number
CN202510682870.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-05-26
Publication Date
2025-08-19

AI Technical Summary

Technical Problem

The existing methods have problems of nonlinear geometric distortion, depth information loss and occlusion ambiguity in the reconstruction of the monocular clothing body of the perspective image, making it difficult to achieve high-precision reconstruction of the clothing body.

Method used

Using fusion distortion correction, three-dimensional geometric representation and pseudo-multi-view constraints, a multi-scale attention enhancement network is designed, and a high-precision human body reconstruction model is generated by combining Fourier transform and pseudo-multi-view feature fusion.

Benefits of technology

It effectively alleviates the impact of perspective distortion, improves the geometric accuracy and detail fidelity of three-dimensional human body reconstruction, and improves the reconstruction quality under perspective distortion images.

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

Abstract

The invention discloses a perspective distortion image-oriented monocular dressing human body reconstruction method, and relates to the technical field of three-dimensional vision. The invention provides a three-dimensional human body reconstruction framework fusing distortion correction, three-dimensional geometric representation and pseudo multi-view constraint, and image distortion is relieved by uniformly partitioning an image and using virtual view transformation to decouple the relevance between an image position and perspective distortion; a multi-scale attention enhancement network is designed, and a hourglass model and a channel attention mechanism are utilized to extract block features, so that the model can process perspective distortion images; the human body parameter model is coded into a frequency domain coefficient through Fourier transform, and the frequency domain coefficient serves as the basis of geometric representation; in order to further optimize high-frequency details, the invention provides a pseudo multi-view module, and the robustness of the network to perspective distortion is enhanced by simulating multi-view data enhancement. Experimental results show that compared with the prior art, the method disclosed by the invention has the advantages that the quantification and the qualitative property on the Thuman2.0 data set and the CumHumans data set are optimal.
Need to check novelty before this filing date? Find Prior Art