Neuralangelo: High-Fidelity Neural Surface Reconstruction

By Zhaoshuo Li, T. Muller, Alex Evans, Russell H. Taylor, Mathias Unberath, Ming-Yu Liu, Chen-Hsuan Lin. Computer Vision and Pattern Recognition, 2023

628 citations recorded by the source corpus.

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.

Subfields: Computational Mechanics, Computer Graphics and Computer-Aided Design, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/06e9b41222dbf2bcea05d3757c73aff68cdcc258

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

In Computer Graphics and Computer-Aided Design

In Computer Vision and Pattern Recognition

Citations in the corpus

NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstruction (2022, background): “Neuralangelo [28] presents a novel Instant-NGP Instant-NGP: post-process Ours Ours: w/o Eikonal”
2D Gaussian Splatting for Geometrically Accurate Radiance Fields (2024, positive): “Moreover, the training and representational power of NeRF have been enhanced using feature-grid based scene representations [Chen et al. 2022, 2023c; Fridovich-Keil et al. 2022; Liu et al. 2020; Müller et al. 2022; Sun et al. 2022a].”
SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering (2023, methodology): “Retrieving such an editable mesh for realistic rendering is done within minutes with our method, compared to hours with the state-of-the-art method on SDFs, while providing a better rendering quality.”
PGSR: Planar-Based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstruction (2024, positive): “Moreover, our training speed only requires one hour on a single GPU, while the state-of-the-art method based on NeRF [18] requires eight GPUs over two days.”
GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting (2023, neutral): “However, optimizing NeRF can be time-consuming, despite its wide usage in 3D reconstruction [3, 6, 13, 21, 44] and generation [22, 35] tasks.”
VastGaussian: Vast 3D Gaussians for Large Scene Reconstruction (2024, neutral): “…becomes a popular 3D representation for photo-realistic novel-view synthesis in recent years [35], many variants are proposed to improve quality [2–4, 24, 45, 47–49, 57], increase speed [8, 9, 11, 14, 20, 32, 36, 37, 40, 43, 46, 58, 60], extend to dynamic scenes [7, 15, 18, 25, 27, 50], and so on.”
DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation (2023, methodology): “…various aspects such as generation fidelity and training stability (Lin et al., 2023; Tsalicoglou et al., 2023; Zhu & Zhuang, 2023; Yu et al., 2023; Li et al., 2023c; Chen et al., 2023d; Wang et al., 2023b; Huang et al., 2023; Metzer et al., 2022; Chen et al., 2023c), and explore further…”
Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction (2023, background): “…through the use of MLPs. Subsequent research has expanded the utility of NeRF to various applications, encompassing tasks such as mesh reconstruction from a collection of images [20, 45], inverse rendering [5, 25, 54], optimization of camera parameters [21, 47, 48], and few-shot learning [10, 51].”
Octree-GS: Towards Consistent Real-time Rendering with LOD-Structured 3D Gaussians (2024, methodology): “Inspired by the progressive training strategy commonly used in prior NeRF methods [28], [51], [56], we implement a coarse-to-fine optimization strategy. begins by training on a subset of anchors representing lower LOD levels and progressively activates finer LOD levels throughout optimization,…”
Gen3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control (2025, neutral): “Generating novel views from a set of posed images has seen significant progress [25, 35, 50], with numerous extensions towards large scene reconstruction [3, 28, 62, 71], improved rendering quality [2, 21, 58], faster rendering speed [37, 58] and handling dynamic scenes [11, 32].”
Gaussian Opacity Fields: Efficient Adaptive Surface Reconstruction in Unbounded Scenes (2024, methodology): “The results of implicit methods are taken from Neuralangelo [Li et al. 2023] and the results of explicit methods are taken from 2DGS [Huang et al. 2024], where the mesh of 3DGS [Kerbl et al. 2023] and 2DGS [Huang et al. 2024] are extracted with TSDF fusion and SuGaR uses Poisson reconstruction.”