Efficiently combining positions and normals for precise 3D geometry

By Diego F. Nehab, Szymon Rusinkiewicz, James Davis, Ravi Ramamoorthi. 2005

493 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computational Mechanics, Computer Graphics and Computer-Aided Design

How researchers see this paper

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

In Aerospace Engineering

In Computational Mechanics

In Computer Graphics and Computer-Aided Design

Citations in the corpus

Consolidation of unorganized point clouds for surface reconstruction (2009, background): “Aside from estimating point normals via purely geometric means, acquisition mechanisms such as photometric stereo [Woodham 1980; Nehab et al. 2005] are also possible but they are often subject to error caused by surface or illumination artifacts.”
Reconstruction of Personalized 3D Face Rigs from Monocular Video (2016, methodology): “The final vertex normals are computed by averaging over a temporal window of size 5 for stability [Nehab et al. 2005].”
Fast and Effective Feature-Preserving Mesh Denoising (2007, methodology): “X. Sun is with the School of Computer Science, Cardiff University, Queen’s Buildings, 5 The Parade, Roath, Cardiff CF24 3AA, UK, and the School of Automation Science and Electrical Engineering, Beihang University, Beijing 100083, P.R. China.”
Curve skeleton extraction from incomplete point cloud (2009, methodology): “Point normals can be acquired via photometric stereo [Nehab et al. 2005] or computed from unorganized points via a normal estimation and orientation scheme, e.”
Fourier Analysis of the 2D Screened Poisson Equation for Gradient Domain Problems (2008, background): “Several papers combine depth information with normals to improve depth map reconstruction [14–16].”
Deep Depth Completion of a Single RGB-D Image (2018, methodology): “However, we can approximate this error term with a linear formation by foregoing the vector normalization, as suggested in [50].”
Multiview Photometric Stereo (2008, methodology): “In [7], a very good initial approximation to the object surface is obtained using range scanning technology which, however, is shown to suffer from high-frequency noise.”
3D Morphable Face Models—Past, Present, and Future (2019, unknown): “Nehab et al. [2005] propose a method for merging the low”
Learning to reconstruct shape and spatially-varying reflectance from a single image (2018, result): “From Figure 6, we can see that the error of depth prediction is significantly larger than the normal prediction, which suggests that we may use normal predictions to refine depth predictions [Nehab et al. 2005].”
DeepHuman: 3D Human Reconstruction From a Single Image (2019, methodology): “We obtain the final reconstruction result by first extracting a triangular polygon mesh from the occupancy volume using the Marching Cube algorithm and then refining the mesh according to the normal map using the method in [37].”
Real-time shading-based refinement for consumer depth cameras (2014, background): “Photometric stereo has demonstrated compelling reconstructions of surfaces with complex reflectance properties [Mulligan and Brolly 2004; Hernández et al. 2008; Ghosh et al. 2011; Tunwattanapong et al. 2013; Debevec 2012; Bermano et al. 2014; Nehab et al. 2005].”