Filling holes in complex surfaces using volumetric diffusion

By James Davis, Steve Marschner, Matthew Garr, Marc Levoy. Proceedings. First International Symposium on 3D Data Processing Visualization and Transmission, 2002

573 citations recorded by the source corpus.

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

View Paper: https://www.semanticscholar.org/paper/d8b9e8fafc16d84ff580d63cad17ab82f8e21dbc

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

Citations in the corpus

Structured Prediction of Unobserved Voxels from a Single Depth Image (2016, background): “[9] complete surfaces by operating directly on the signed distance field, the zero level-set of which defines the surface location.”
The space of human body shapes: reconstruction and parameterization from range scans (2003, background): “DeCarlo et al. [1998] use a corpus of anthropometric facial measurements to model the variation in face shapes.”
Dynamic shape capture using multi-view photometric stereo (2009, methodology): “Several approaches have been proposed to fill such holes, using techniques such as space carving [Curless and Levoy 1996] and volumetric diffusion [Davis et al. 2002].”
Morphing and Sampling Network for Dense Point Cloud Completion (2019, background): “Geometry-based approaches may interpolate smooth surfaces based on existing structures (Davis et al. 2002; Zhao, Gao, and Lin 2007) or rely on some geometric assumptions, such as symmetry (Thrun and Wegbreit 2005; Sipiran, Gregor, and Schreck 2014).”
Robust repair of polygonal models (2004, methodology): “We are also investigating incorporation of diffusionbased methods [Davis et al. 2002] for creating more natural looking patches on the dual surface with the surrounding geometry.”
State of research in automatic as-built modelling (2015, background): “in filling holes [38,96], but it has difficulties in recovering sharp features.”
A robust hole-filling algorithm for triangular mesh (2007, methodology): “[7] used volumetric diffusion to fill the gaps and Curless et al.”
PCN: Point Completion Network (2018, methodology): “For example, surface reconstruction methods [3, 10, 33, 41, 49, 54, 62] generate smooth interpolations to ﬁll holes in locally incomplete scans.”
Reconstruction of textureless regions using structure from motion and image-based interpolation (2014, unknown): “Volumetric diffusion is used in [9].”
A Field Model for Repairing 3D Shapes (2016, background): “In [7], Davis et al. filled gaps and holes on broken surfaces by performing a convolution on the signed distance values.”
Automatic Creation of Semantically Rich 3D Building Models from Laser Scanner Data (2011, background): “The general problem of reconstructing occluded surfaces in 3D is also known as “hole ﬁlling,” and there are many proposed solutions (Davis et al., 2002; Salamanca et al., 2008).”
SCAPE: shape completion and animation of people (2005, background): “A common way to complete these holes is to fill them with a smooth surface patch that meets the boundary conditions of the hole [Curless and Levoy 1996; Davis et al. 2002; Liepa 2003].”
Optimal Step Nonrigid ICP Algorithms for Surface Registration (2007, background): “[5], which are able to close holes by interpolating between the borders.”