This work introduces a novel augmentation method that increases the diversity of a train set to improve the generalization abilities of a 6D pose estimation network. For this purpose, a Neural Radiance Field is trained on synthetic images and exploited to generate an augmented set. Our method enriches the initial set by enabling the synthesis of images with (i) unseen viewpoints, (ii) rich illumination conditions through appearance extrapolation, and (iii) randomized textures. We validate our method on the spacecraft pose estimation use-case and show that it significantly improves the generalization capabilities. On the SPEED+ dataset, our method reduces the error on the pose by 50% on both target domains.