Coloring the Past: Neural Historical Buildings Reconstruction from Archival Photography

TL;DR

This paper presents a neural rendering approach for reconstructing 3D models of historical buildings from limited archival photographs, addressing challenges like dataset scarcity and image quality, and introduces a new dataset for benchmarking.

Contribution

It introduces a novel volumetric rendering method utilizing dense point clouds and a color embedding loss, along with a new Hungarian National Theater dataset for historical building reconstruction.

Findings

Effective reconstruction of historical buildings from limited data

Introduction of a new benchmark dataset for the task

Demonstrated improved color and geometry recovery

Abstract

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.