Three-dimensional reconstruction method and apparatus, terminal, and storage medium
AssigneesBeijing Zitiao Network Technology Co., Ltd., Peking University
InventorsChenguo LIN, Panwang PAN, Yadong MU
Life of this patent
Estimating the term…
Abstract
The present disclosure provides a three-dimensional reconstruction method and apparatus, a terminal, and a storage medium. The three-dimensional reconstruction method includes: inputting a single-view image and a camera position thereof into a trained diffusion model; outputting, by the diffusion model, three-dimensional Gaussian splatting parameters corresponding to an object in the single-view image; and performing three-dimensional object rendering using the three-dimensional Gaussian splatting parameters, to obtain a reconstructed three-dimensional object
Claims20
A three-dimensional reconstruction method, comprising:
- inputting a single-view image and a camera position of the single-view image into a trained diffusion model;
- outputting, by the diffusion model, three-dimensional Gaussian splatting parameters corresponding to an object in the single-view image;
- and
- performing three-dimensional object rendering by using the three-dimensional Gaussian splatting parameters, to obtain a reconstructed three-dimensional object.
A terminal, comprising
- at least one memory and at least one processor,
- wherein the at least one memory is configured to store program code which, when executed by the at least one processor, causes the at least one processor to:
- input a single-view image and a camera position of the single-view image into a trained diffusion model;
- output, by the diffusion model, three-dimensional Gaussian splatting parameters corresponding to an object in the single-view image;
- and
- perform three-dimensional object rendering by using the three-dimensional Gaussian splatting parameters, to obtain a reconstructed three-dimensional object.
A non-transitory storage medium, wherein the storage medium is configured to store program code which, when executed by a computer, causes the computer to:
- input a single-view image and a camera position of the single-view image into a trained diffusion model;
- output, by the diffusion model, three-dimensional Gaussian splatting parameters corresponding to an object in the single-view image;
- and
- perform three-dimensional object rendering by using the three-dimensional Gaussian splatting parameters, to obtain a reconstructed three-dimensional object.
Dependencies are inferred from the claim text.