This work proposes a method bridging the existing gap between progressive sparse 3D reconstruction (incremental Structure from Motion) and progressive point based dense 3D reconstruction (Multi-View Stereo). The presented algorithm is capable of adapting an existing dense 3D model to changes such as the addition or removal of new images, the merge of scene parts, or changes in the underlying camera calibration. The existing 3D model is transformed as consistently as possible and the structure is reused as much as possible without scarifying the quality and/or accuracy of the final result. A significant decrease in runtime is achieved compared to the re-computation of a new dense point cloud from scratch. We demonstrate the performance of the algorithm in various experiments on publicly available datasets of different sizes and compare it to the baseline. The work interacts seamlessly with publicly available software enabling an integrated progressive 3D modeling pipeline.