CVPR Findings2026
SwiftNDC: Fast Neural Depth Correction for High-Fidelity 3D Reconstruction
Kang Han, Wei Xiang, Lu Yu, Mathew Wyatt, Gaowen Liu, Ramana Rao Kompella
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. 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)-based 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.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- Instant neural graphics primitives with a multiresolution hash encoding cites Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields
- 3D Gaussian Splatting for Real-Time Radiance Field Rendering cites Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields
- 3D Gaussian Splatting for Real-Time Radiance Field Rendering cites Instant neural graphics primitives with a multiresolution hash encoding
Builds on22
- 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 5,687 citations
- Instant neural graphics primitives with a multiresolution hash encodingThomas Müller, Alex Evans, Christoph Schied, Alexander KellerSIGGRAPH 2022 · 4,089 citations
- Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance FieldsJonathan T. Barron, Ben Mildenhall, Matthew Tancik, Peter Hedman et al.ICCV 2021 · 2,700 citations
- NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view ReconstructionPeng Wang, Lingjie Liu, Yuan Liu, Christian Theobalt et al.NeurIPS 2021 · 2,500 citations
- Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance FieldsJonathan T. Barron, Ben Mildenhall, Dor Verbin, Pratul P. Srinivasan et al.CVPR 2022 · 1,603 citations
Related papers
- VCR-GauS: View Consistent Depth-Normal Regularizer for Gaussian Surface ReconstructionHanlin Chen, Fangyin Wei, Chen Li, Tianxin Huang et al.NeurIPS 2024 · 71 citations
- Neural Signed Distance Function Inference through Splatting 3D Gaussians Pulled on Zero-Level SetWenyuan Zhang, Yu-Shen Liu, Zhizhong HanNeurIPS 2024 · 58 citations
- DGS: Depth-and-Density Guided Gaussian Splatting for Stable and Accurate Sparse-View ReconstructionMeixi Song, Xin Lin, Dizhe Zhang, Haodong Li et al.ICLR 2026 · 5 citations
- FastGS: Training 3D Gaussian Splatting in 100 SecondsShiwei Ren, Tianci Wen, Yongchun Fang, Biao LuCVPR 2026 · 55 citations
- 2D Gaussian Splatting for Geometrically Accurate Radiance FieldsBinbin Huang, Zehao Yu, Anpei Chen, Andreas Geiger et al.SIGGRAPH 2024 · 660 citations
