Abstract

Most of the image-based modelling and rendering works rely on the input supplied by the user. It becomes necessary to optimise the user interaction while building the 3D model. We present an interactive system for image-based 3D modelling from single view uncalibrated images based on depth-cueing. The depth information is interpreted by drawing a grey line with highest intensity at the vertices closer to viewing point and proportionally decreasing towards the vertices farther. On the rendering part, the perspective distortion is rectified on each surface based on projective transformation by exploiting the presence of symmetric objects in the images to get the fronto-parallel view. The significance of symmetric objects in a scene to rectify the perspective distortion is demonstrated. The rectified surfaces are used to retrieve the actual 3D coordinates of the wireframe and also used as texture maps during rendering to get the photo realistic results.

Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call