Coloring the Past: Neural Historical Buildings Reconstruction from Archival Photography
This work addresses the preservation of cultural heritage by enabling 3D reconstruction of historical buildings from challenging archival data, though it is incremental as it builds on existing neural rendering techniques.
The paper tackles the problem of reconstructing 3D models of historical buildings from archival photographs, which are limited in number and quality, by introducing a method that uses volumetric rendering with dense point clouds and a color appearance embedding loss, achieving reconstruction with recovered color from limited color images.
Historical buildings are a treasure and milestone of human cultural heritage. Reconstructing the 3D models of these building hold significant value. The rapid development of neural rendering methods makes it possible to recover the 3D shape only based on archival photographs. However, this task presents considerable challenges due to the limitations of such datasets. Historical photographs are often limited in number and the scenes in these photos might have altered over time. The radiometric quality of these images is also often sub-optimal. To address these challenges, we introduce an approach to reconstruct the geometry of historical buildings, employing volumetric rendering techniques. We leverage dense point clouds as a geometric prior and introduce a color appearance embedding loss to recover the color of the building given limited available color images. We aim for our work to spark increased interest and focus on preserving historical buildings. Thus, we also introduce a new historical dataset of the Hungarian National Theater, providing a new benchmark for the reconstruction method.