Pseudo-real Image Sequence Generator for Optical Flow Computations

Abstract

The availability of ground-truth flow field is crucial for quantitative evaluation of any optical flow computation method. The fidelity of test data is also important when artificially generated. Therefore, we generated an artificial flow field together with an artificial image sequence based on real-world sample image. The presented framework benefits of a two-layered approach in which user-selected foreground was locally moved and inserted into an artificially generated background. The background is visually similar to input sample image while the foreground is extracted from original and so is the same. The framework is capable of generating 2D and 3D image sequences of arbitrary length. Several examples of the version tuned to simulate real fluorescent microscope images are presented. We also provide a brief discussion.

Virtual cell imaging: A review on simulation methods employed in image cytometry

“…Learning‐based frameworks capable of producing plausible time‐lapse sequences have been developed as an alternative to parametric‐based phantoms based on composition and manipulation with basic geometrical structures. Here, the synthetic image sequences are often created by iteratively preparing flow fields, therein introducing various types of motion and deformations that are applied to the given initial real input (training) image .…”