As-rigid-as-possible surface modeling

By Olga Sorkine-Hornung, Marc Alexa. Eurographics Symposium on Geometry Processing, 2007

1,438 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/5e9f41ebb3a5c5ca0905734f3698ab18d9988bea

How researchers see this paper

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

Citations in the corpus

SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes (2023, unknown): “In order to maintain the local rigidity, we perform ARAP [41] deformation on the control graph based on constraints specified by users.”
Elastic Fragments for Dense Scene Reconstruction (2013, background): “where N (p) is the set of neighbors of p in Gi, and Rp is a rotation transform that maps the local tangent frame of p to the local tangent frame of p′ [28, 30].”
Nerfies: Deformable Neural Radiance Fields (2020, methodology): “It is common in geometry processing and physics simulation to model non-rigid deformations using elastic energies measuring the deviation of local deformations from a rigid motion [8, 13, 51, 52].”
Non-Rigid Neural Radiance Fields: Reconstruction and Novel View Synthesis of a Dynamic Scene From Monocular Video (2020, methodology): “Inspired by local, isometric shape preservation from computer graphics, like as-rigid-as-possible regularization for surfaces [73, 27] or volume preservation for volumes [71], we seek to preserve the local shape after deformation.”
Deep Single-Image Portrait Relighting (2019, methodology): “A novel As-Rigid-As-Possible-based (ARAP-based) [27] warping method is then proposed to accurately align the estimated face normal to the portrait image.”
Registration of 3D Point Clouds and Meshes: A Survey from Rigid to Nonrigid (2013, methodology): “[28] extend the method to larger deformations by extracting an urshape [79], and using a nonlinear as-rigid-as-possible model [42] for deformation.”
Spatial adaption of robot trajectories based on laplacian trajectory editing (2015, methodology): “2.1), the ARAP optimization (Sorkine and Alexa 2007)”
NeRF-Editing: Geometry Editing of Neural Radiance Fields (2022, methodology): “In this paper, we use the classic ARAP (as-rigid-as-possible) deformation method [59] to enable users to interactively deform the mesh.”
PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamics (2023, methodology): “7, we conduct a comparison study between our method and NeRF-Editing [51], which utilizes surface As-Rigid-As-Possible (ARAP) deformation [38].”
3D Menagerie: Modeling the 3D Shape and Pose of Animals (2016, methodology): “Consequently the GLoSS alignment is followed by a model-free step where the template mesh vertices deform towards the scan surface under a As-Rigid-As-Possible (ARAP) constraint [27].”
VolumeDeform: Real-Time Volumetric Non-rigid Reconstruction (2016, methodology): “To this end, we impose the as-rigid-as-possible (ARAP) [18] prior on the grid: Here, N i is the one-ring neighborhood of the i th grid point and M is the set of all grid points used during optimization.”
Completing 3D object shape from one depth image (2015, methodology): “[34, 33, 10, 40, 4]) or are restricted to a limited set of objects or categories (e.”
User-Specific Hand Modeling from Monocular Depth Sequences (2014, background): “The as-rigid-as-possible (ARAP) measure [22, 11] is defined as”
Surface Networks (2017, methodology): “We consider the mesh a thin elastic shell, and we simulate it using the As-Rigid-As-Possible technique [35], with additional gravitational forces [17].”