Neuralangelo: High-Fidelity Neural Surface Reconstruction

TLDR

Neural surface reconstruction has proven powerful for dense 3D surface recovery via image-based neural rendering, yet existing methods struggle to capture detailed structures in real-world scenes. To overcome this limitation, we introduce Neuralangelo, which fuses multiresolution 3D hash grids with neural surface rendering. The method employs numerical gradients for higher‑order derivative smoothing and a coarse‑to‑fine optimization scheme across hash grid levels to control detail. Neuralangelo recovers dense 3D surface structures from multiview images with fidelity that surpasses prior approaches, enabling detailed large‑scale scene reconstruction from RGB video captures.

Abstract

Neural surface reconstruction has been shown to be powerful for recovering dense 3D surfaces via image-based neural rendering. However, current methods struggle to recover detailed structures of real-world scenes. To address the issue, we present Neuralangelo, which combines the representation power of multiresolution 3D hash grids with neural surface rendering. Two key ingredients enable our approach: (1) numerical gradients for computing higher-order derivatives as a smoothing operation and (2) coarse-to-fine optimization on the hash grids controlling different levels of details. Even without auxiliary inputs such as depth, Neuralangelo can effectively recover dense 3D surface structures from multiview images with fidelity significantly surpassing previous methods, enabling detailed large-scale scene reconstruction from RGB video captures.