Towards a Standalone Methodology for Robust Algorithms Evaluation: A Case Study in 3D Reconstruction

In the field of 3D reconstruction there are two main challenging tasks that require careful consideration, namely, feature detection and matching. The corresponding automatic process introduces noise resulting from the image capture and spurious features matching. A number of robust algorithms for hypothesis evaluation have been suggested, they would deal with these limitations by removing outliers. Most of these works are merely comparisons to previous algorithms and lack any standalone evaluation. This paper attempts to fill this gap by introducing a novel and robust statistical methodology. It has the advantage of evaluating related algorithms using non-dimensional metrics for fixed and continuous intervals. In addition, the proposed methodology is validated using a proof of concept scenario based on the 3D pose estimation phase in the 3D reconstruction pipeline. The obtained results are very promising and emphasize the methodology's generic nature, clearing the way for its application in a multitude of scenarios, such as computer vision and 3D reconstruction.