Frequency and tensorial neural radiance fields for digital preservation of ancient buildings

Ancient buildings are invaluable cultural heritage assets, traditional preservation methods often suffer from inefficiency and low accuracy. We propose FaTNeRF, a NeRF-based framework that integrates adaptive frequency encoding and a novel density loss for high-quality rendering and digital preservation. Evaluations on public datasets show our method achieves fast reconstruction (<20 min) with superior visual quality while maintaining compact model size (<75 MB). Additional validation on a self-collected cultural heritage dataset confirms its effectiveness in complex real-world scenarios. FaTNeRF advances digital preservation by enabling efficient, high-fidelity 3D reconstruction for historic buildings.