The collection of as-built data for construction progress monitoring remains challenging. This paper develops two case studies on image-based modeling, in which point cloud models are created based on the photo collection of the construction site. The first case considers 399 unordered construction images previously taken for purposes other than progress monitoring, whereas the second case considers 118 photos that have been taken based on the results of the first case study. The results of the first case study are employed to improve the quality of the point cloud model in the second case, using the site photo collection captured by the first author for the purpose of establishing an enhanced point cloud model. The results of the two case studies are compared. Furthermore, the results are compared with those of other researchers and found that they are in a good agreement with other reported results. Finally, some suggestions are proposed to improve the image-based model for construction progress monitoring, particularly for industrial projects that involve a large construction site and various work packages.