Precise reconstruction of 3D volumes from X-ray projections requires precisely pre-calibrated systems where accurate knowledge of system geometric parameters is known ahead. However, when dealing with mobile X-ray devices such calibration parameters are unknown. Joint estimation of system calibration parameters and 3d reconstruction is heavily unconstrained problem, especially when the projections are arbitrary. In industrial applications, that we target here, nominal CAD models of object to be reconstructed are usually available. We rely on this prior information and employ Deep Learning to learn the mapping between simulated X-ray projections and its pose. Moreover, we introduce the reconstruction loss in addition to the pose loss to further improve the reconstruction quality. Finally, we demonstrate the generalization capabilities of our method in case where poses can be learned on instances of the objects belonging to the same class, allowing pose estimation of unseen objects from the same category, thus eliminating the need for the actual CAD model. We performed exhaustive evaluation demonstrating the quality of our results on both synthetic and real data.     «

Precise reconstruction of 3D volumes from X-ray projections requires precisely pre-calibrated systems where accurate knowledge of system geometric parameters is known ahead. However, when dealing with mobile X-ray devices such calibration parameters are unknown. Joint estimation of system calibration parameters and 3d reconstruction is heavily unconstrained problem, especially when the projections are arbitrary. In industrial applications, that we target here, nominal CAD models of object to be...     »