Pose-invariant view synthesis using image-based visual hull

In this paper, we introduce an active view synthesis approach using image-based visual hull. With the virtual camera moving on a properly selected circular trajectory around an object of interest, we achieve a collection of virtual views of the object, which is equivalent to the case that the object is on a rotating turntable and captured by a static camera whose optical axis is parallel to the turntable. We show how to derive the virtual camera's extrinsic parameters at each position on the trajectory. With template matching method, this approach can be used to generate the desired pose-invariant images for recognition applications.