Proceedings of the 27th annual conference on Computer graphics and interactive techniques
Proceedings of the 27th annual conference on Computer graphics and interactive techniques
A Computational Framework for Determining Stereo Correspondence from a Set of Linear Spatial Filters
ECCV '92 Proceedings of the Second European Conference on Computer Vision
Image Processing, Analysis, and Machine Vision
Image Processing, Analysis, and Machine Vision
Hi-index | 0.00 |
We present a very inexpensive way of creating dynamic image-based renderings of digitally recorded, photo realistic, real-life objects. Together with computer vision algorithms, the recorded person is visualized using the Relief Texture Mapping algorithm [Oliveira et al. 2000]. This mapping technique requires depth information for all texels representing the recorded object from all recorded views. By using two digital video cameras, the dynamic object is recorded in stereo in different views to cover its whole volume. As the depth information from the separate views is generated by stereo correlation, it is used together with the recorded video as relief textures on a pre-defined bounding box and morphed into a three dimensional representation by justifying the known depth disparities.