SwiftNDC: Fast Neural Depth Correction for High-Fidelity 3D Reconstruction
This work addresses the problem of scale drift and multi-view inconsistencies in depth-guided 3D reconstruction for researchers and practitioners aiming for high-fidelity and efficient 3D models.
This paper introduces SwiftNDC, a framework that uses a Neural Depth Correction field to generate cross-view consistent depth maps, which are then used to create a dense point cloud. This refined geometry significantly accelerates 3D Gaussian Splatting (3DGS) for mesh reconstruction and improves rendering quality for novel-view synthesis across five datasets.
Depth-guided 3D reconstruction has gained popularity as a fast alternative to optimization-heavy approaches, yet existing methods still suffer from scale drift, multi-view inconsistencies, and the need for substantial refinement to achieve high-fidelity geometry. Here, we propose SwiftNDC, a fast and general framework built around a Neural Depth Correction field that produces cross-view consistent depth maps. From these refined depths, we generate a dense point cloud through back-projection and robust reprojection-error filtering, obtaining a clean and uniformly distributed geometric initialization for downstream reconstruction. This reliable dense geometry substantially accelerates 3D Gaussian Splatting (3DGS) for mesh reconstruction, enabling high-quality surfaces with significantly fewer optimization iterations. For novel-view synthesis, SwiftNDC can also improve 3DGS rendering quality, highlighting the benefits of strong geometric initialization. We conduct a comprehensive study across five datasets, including two for mesh reconstruction, as well as three for novel-view synthesis. SwiftNDC consistently reduces running time for accurate mesh reconstruction and boosts rendering fidelity for view synthesis, demonstrating the effectiveness of combining neural depth refinement with robust geometric initialization for high-fidelity and efficient 3D reconstruction.