Image-based rendering of range data with depth uncertainty

Image-based rendering is an exciting new field that lies between computer graphics and computer vision. The more we use the knowledge from computer vision in our graphics rendering algorithms, the better our final rendered images will be. This dissertation presents a framework to identify what information from computer vision is relevant for rendering and how to render this information.; Instead of only using the depth information per pixel, we compute what we call a depth uncertainty region around it. We show how to compute this region from an existing 3-D recovery algorithm called range-space search. We also present a new idea that further improves the uncertainty estimation based on the assumption that the estimated depth is close enough to the actual surface.; Finally, we present two approaches for rendering. The 4-D approach is based on the light field ray space parameterization. The 3-D approach is based on an existing technique for splatting 3-D Gaussian kernels. We show that both techniques achieve good results and that the 3-D approach is faster and produces sharper images in most cases.