Mesh editing with poisson-based gradient field manipulation

By Yizhou Yu, Kun Zhou, Dong Xu, Xiaohan Shi, Hujun Bao, Baining Guo, Harry Shum. 2004

677 citations recorded by the source corpus.

Subfields: 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 Computational Mechanics

In Computer Graphics and Computer-Aided Design

Citations in the corpus

Fast and Effective Feature-Preserving Mesh Denoising (2007, methodology): “Although that algorithm uses the vector median operation to find a normal whose corresponding face shares the same surface with Fi, we simplify this operation and use ni as nm in (4).”
Extreme 3D Face Reconstruction: Seeing Through Occlusions (2017, methodology): “We then use Poisson blending to recover this occluded point [36, 57]:”
Extreme 3D Face Reconstruction: Looking Past Occlusions (2017, methodology): “We then use Poisson blending to recover this occluded point [34, 52]:”
3D Mesh Labeling via Deep Convolutional Neural Networks (2015, methodology): “This step, denoted as mesh labeling, aims to infer the inherent characteristics of the mesh and can be applied to various applications such as mesh editing [Yu et al. 2004; Chen et al. 2015a], modelling [Chen et al.”
Multilinear pose and body shape estimation of dressed subjects from image sets (2010, methodology): “We refine the initial 3D mesh by Laplace deformation [4, 21] so that the 3D correspondences of the markers are located on the projection rays of their 2D image positions.”
SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes (2023, methodology): “…field and query the transformation of each control point p k at each timestep t as: Note that in practical implementations, R ti is represented equivalently as a quaternion r ti for more stable optimization and convenient interpolation for generating the motions of Gaussians in the follow-up steps.”
As-rigid-as-possible shape manipulation (2005, methodology): “This process is very similar to the assembly process in [Alexa et al. 2000; Sumner and Popovic 2004; Yu et al. 2004].”
NeRF-Editing: Geometry Editing of Neural Radiance Fields (2022, methodology): “Traditional mesh deformation methods are based on Laplacian coordinates [35, 57, 58], Poisson equation [79], and dual Laplacian coordinates [2].”
Deep Learning 3D Shape Surfaces Using Geometry Images (2016, neutral): “The gradient vector ∇g for each face is solved as [33]: ⎡ ⎣ v − u w − v n ⎤ ⎦∇g = ⎡ ⎣ gv − gu gw − gv 0 ⎤ ⎦”
A robust hole-filling algorithm for triangular mesh (2007, methodology): “In our implementation, we choose the Poisson equation with Dirichlet boundary conditions [18, 22] to refine the patch mesh.”
Mesh-based inverse kinematics (2005, methodology): “The encoding scheme used by the Poisson mesh editing technique [Yu et al. 2004] is an alternative to ours that may perform well for our problem since it was successfully used for mesh interpolation [Xu et al. 2005].”
Linear rotation-invariant coordinates for meshes (2005, methodology): “In the past years several mesh editing techniques were introduced [Zorin et al. 1997; Kobbelt et al. 1998; Guskov et al. 1999; Lee 1999; Bendels and Klein 2003; Botsch and Kobbelt 2004; Lipman et al. 2004; Sheffer and Kraevoy 2004; Sorkine et al. 2004; Yu et al. 2004; Zayer et al. 2005].”