Direct filtering method for image based rendering

Abstract

Image based rendering (IBR) is basically a light ray resampling method for generating a novel image without aliasing artifacts from a given set of sampled light rays. To avoid aliasing artifacts, conventional methods require an estimate of the scene geometry. In this paper, we present a novel IBR method by linear filtering without estimating the scene geometry, for the simplified case when generating a virtual image at the center of 2× 2 sparse camera array for a two depth-layers scene. The reconstruction filter used in the proposed method can derived by integrating all the process in our previously proposed method into an one-shot process.

Arbitrary viewpoint image synthesis on multi-layered scene using reconstruction filters

“…The reconstruction filtering method is one approach for avoiding this difficulty, in which captured images are filtered to obtain an arbitrary viewpoint image as the summation of these filtered images [4]. This method does not require the shape prediction such as distance estimation, but assumes that subjects exist on predetermined planes.…”