SwiftNDC: Fast Neural Depth Correction for High-Fidelity 3D Reconstruction

TL;DR

SwiftNDC introduces a neural depth correction framework that enhances 3D reconstruction accuracy and speed by providing consistent depth maps, leading to improved mesh quality and faster processing across multiple datasets.

Contribution

It presents a novel neural depth correction method that improves geometric initialization, accelerates 3D reconstruction, and enhances rendering quality in view synthesis.

Findings

Reduces reconstruction time significantly.

Improves mesh and rendering quality.

Demonstrates effectiveness across diverse datasets.

Abstract

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.