| 摘要 |
Systems and methods are described for retexturing portions of surface in a 2-D image, where the surface is an image of a 3-D object. The systems and methods analyze, with user input, the 2-D image and then, in computer memory, generate a 3-D model of the imaged surface. The surface may then be retextured, that is, for example, artwork may be added to the 2-D image in a realistic manner, taking into account a 3-D geometry in the scene of the 2-D image. |
| 主权项 |
1. A method implemented on a computer having memory, a processor, and a display, where the method includes:
accepting a file containing a 2-D image of a 3-D scene into memory, where the 2-D image includes a 2-D surface that is an image of a 3-D surface of an object in the 3-D scene; generating a 3-D model to approximate the 3-D surface of the object in the 3-D scene, where said generating includes:
forming a perspective model, where the perspective model includes a mathematical transformation for: 1) projecting points from the 3-D model to the 2-D image, and 2) re-projecting points from the 2-D image to the 3-D scene,defining a first silhouette segment of the 2-D surface,defining a second silhouette segment of the 2-D surface,defining one or more profile curves each extending from the first silhouette segment to the second silhouette segment,identifying a spine disposed between said first segment and said second segment,re-projecting the spine to a 3-D spine in the 3-D scene,obtaining geometric information related to the object in the scene,re-projecting each of said one or more profile curves to a corresponding 3-D profile curve, where each 3-D profile curve is in a corresponding profile plane perpendicular to the 3-D spine, where said re-projecting includes using the obtained geometric information,forming a 3-D model by interpolating the one or more profile segments along the 3-D spine, and displaying the 3-D model on the display. |
