Simulating Structure-from-Motion
This is an incremental study for computer vision researchers focusing on improving SfM accuracy through synthetic data and ground truth integration.
The project tackled the problem of evaluating Structure-from-Motion (SfM) reconstructions by implementing a pipeline using synthetic scenes and comparing camera pose estimations to ground truth, with results including a study on reducing estimation error by injecting ground truth data, though no concrete numbers were provided.
The implementation of a Structure-from-Motion (SfM) pipeline from a synthetically generated scene as well as the investigation of the faithfulness of diverse reconstructions is the subject of this project. A series of different SfM reconstructions are implemented and their camera pose estimations are being contrasted with their respective ground truth locations. Finally, injection of ground truth location data into the rendered images in order to reduce the estimation error of the camera poses is studied as well.