Modulating View-dependent Textures

Abstract

We present a texturing approach for image-based modeling and rendering, where instead of using one (or a blend of a few) sample images, new view dependent textures are synthesized by modulating a differential texture basis. The texture basis models the first order intensity variation due to image projection errors and parallax for a nonlinear projective camera. Experimentally we compare rendered views to ground truth real images and quantify how the texture basis can generate a more accurate rendering compared to conventional view dependent textures.