Poisson surface reconstruction

By M. Kazhdan, Matthew Bolitho, Hugues Hoppe. 2006

3,760 citations recorded by the source corpus.

Subfields: Computer Graphics and Computer-Aided Design, 3D Vision & Pose

How researchers see this paper

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

In Computer Graphics and Computer-Aided Design

In 3D Vision & Pose

Citations in the corpus

Occupancy Networks: Learning 3D Reconstruction in Function Space (2018, background): “However, unlike other representations, this approach requires additional non-trivial post-processing steps [3,6,37,38] to generate the ﬁnal 3D mesh.”
Learning Shape Priors for Single-View 3D Completion and Reconstruction (2018, methodology): “, Poisson surface reconstruction solves an indicator function on a voxel grid via the Poisson equation [29,28].”
Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputs (2017, background): “Octrees have a long history in classical 3D reconstruction and depth map fusion [21, 1, 11, 34, 6, 31].”
Shape Completion Using 3D-Encoder-Predictor CNNs and Shape Synthesis (2016, methodology): “Poisson surface reconstruction [14, 15] is mostly used to obtain complete surfaces on dense point clouds, but it cannot infer missing structures.”
Screened poisson surface reconstruction (2013, methodology): “INTRODUCTION Poisson surface reconstruction [Kazhdan et al. 2006] is a wellknown technique for creating watertight surfaces from oriented point samples acquired with 3D range scanners.”
Matterport3D: Learning from RGB-D Data in Indoor Environments (2017, methodology): “In all, the dataset includes 90 buildings containing a total of 194,400 RGB-D images, 10,800 panorama, and 24,727,520 textured triangles; we provide textured mesh reconstructions obtained with [21] and [25].”
A complete statistical inverse ray tracing approach to multi-view stereo (2011, methodology): “More complete reconstructions are to [5]; (e, f) textured and non-textured models from PMVS2+PoissonRecon [7]; (g, h) textured and non-textured models from our multi-view reconstruction algorithm estimate the region based on the visibility constraints and regularity of the surface geometry. ii)…”
Local Deep Implicit Functions for 3D Shape (2019, methodology): “Thus, traditional surface reconstruction pipelines based on them, such as Poisson Surface Reconstruction [19], require a substantial amount of memory and computation and are not good for completing unobserved regions.”
Accurate, Dense, and Robust Multi-View Stereopsis (2007, methodology): “1) Poisson Surface Reconstruction: Our first approach to mesh initialization is to simply use Poisson Surface Reconstruction (PSR) software [29] that directly converts a set of oriented points into a triangulated mesh model.”
Visual Camera Re-Localization From RGB and RGB-D Images Using DSAC (2020, methodology): “Therefore, we generate a mesh representation using Poisson surface reconstruction [82].”
On benchmarking camera calibration and multi-view stereo for high resolution imagery (2008, neutral): “See Kazhdan [7] for more details.”
Nerfstudio: A Modular Framework for Neural Radiance Field Development (2023, methodology): “6b illustrates our export interface, as well as some of the supported formats, including point clouds, a truncated signed distance function (TSDF) to mesh, and Poisson surface reconstruction [Kazhdan et al. 2006].”
Geo-PIFu: Geometry and Pixel Aligned Implicit Functions for Single-view Human Reconstruction (2020, background): “The drawback is that generating a mesh with ﬁne-scale surface details by Poisson reconstruction [12] requires a huge number of point estimations.”
PU-Net: Point Cloud Upsampling Network (2018, result): “Therefore, we compare the reconstruction result of our method with those baseline methods with direct Poisson surface reconstruction approach [13] implemented in MeshLab [6].”
A textured object recognition pipeline for color and depth image data (2012, methodology): “Given the full 3D point cloud Cyl for object yl, we simulate synthetic views of the point cloud from NJ camera poses {p̂j}, j = 1, ..., NJ around the object.6 For each simulated pose p̂j , we construct a global color histogram descriptor Hj using only points visible from that view.”
SAL: Sign Agnostic Learning of Shapes From Raw Data (2019, background): “[22, 23] solve a Poisson equation on a volumetric discretization to extend points and normals information to an occupancy indicator function.”
Moser Flow: Divergence-based Generative Modeling on Manifolds (2021, background): “, 2012), as well as 3D shapes in computer graphics (Hoppe et al., 1992; Kazhdan et al., 2006).”