Walkthroughs of complex environments using image-based simplification

We present an image-based technique to accelerate the navigation in complex static environments. We perform an image-space simpli cation of each sample of the scene taken at a particular viewpoint and dynamically combine these simpli ed samples to produce images for arbitrary viewpoints. Since the scene is converted into a bounded complexity representation in the image space, with the base images rendered beforehand, the rendering speed is relatively insensitive to the complexity of the scene. The proposed method correctly simulates the kinetic depth e ect (parallax), occlusion, and can resolve the missing visibility information. This paper describes a suitable representation for the samples, a speci c technique for simplifying them, and di erent morphing methods for combining the sample information to reconstruct the scene. We use hardware texture mapping to implement the image-space warping and hardware a ne transformations to compute the viewpoint-dependent warping function.