As-rigid-as-possible shape manipulation

By Takeo Igarashi, Tomer Moscovich, John F. Hughes. ACM Transactions on Graphics, 2005

812 citations recorded by the source corpus.

Subfields: Computational Mechanics, Control and Systems Engineering, Human-Computer Interaction

View Paper: https://www.semanticscholar.org/paper/dd839ecc78330ee07a8237398a21fde1b2122104

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 Control and Systems Engineering

In Human-Computer Interaction

Citations in the corpus

Learning Depth with Convolutional Spatial Propagation Network (2018, methodology): “Later, when we train with more epochs, TABLE 1 Comparison Results on NYU v2 Dataset [14] between Different Variants of CSPN and other State-of-the-Art Strategies Method Preserve “SD” Lower the better Higher the better RMSE REL d1:02 d1:05 d1:10 d1:25 d1:252 d1:253 Ma et al. [10] 0.230 0.044 52.3 82.”
User-Specific Hand Modeling from Monocular Depth Sequences (2014, background): “The as-rigid-as-possible (ARAP) measure [22, 11] is defined as”
Crowds in two seconds: enabling realtime crowd-powered interfaces (2011, methodology): “Puppeteer gives the crowd a rigid shape deformation tool [10], then relies on the crowd to generate plausible deformations based on a text description.”
Shadow art (2009, methodology): “We employ the as-rigid-as possible shape manipulation method of [Igarashi et al. 2005] that computes a smooth deformation of an image using a 2D triangle mesh discretization of the image space.”
Harmonic coordinates for character articulation (2007, positive): “In the area of barycentric coordinates, Ju et al. [2005] used generalized barycentric coordinates, specifically, mean value coordinates (see also Floater et al.”
Depth Estimation via Affinity Learned with Convolutional Spatial Propagation Network (2018, methodology): “(4) for propagation, and the results are shown at row “SPN”, which outperforms both the results form ASAP and SPN without propagation of SD due to joint training helps fix the error of warping.”
Content-preserving warps for 3D video stabilization (2009, methodology): “Recent efforts have focused on deformation controlled by a user who pulls on various handles [Igarashi et al. 2005; Schaefer et al. 2006] while minimizing distortion of local shape, as measured by the local deviation from conformal or rigid transformations.”
DragDiffusion: Harnessing Diffusion Models for Interactive Point-Based Image Editing (2023, neutral): “The framework of point-based editing [5, 19, 43] aims at manipulating images in a fine-grained level.”
As-Projective-As-Possible Image Stitching with Moving DLT (2013, methodology): “For APAP, we varied the scale σ within the range [8 12] for images of sizes 1024 × 768 to 1500 × 2000 pixels.”
On Linear Variational Surface Deformation Methods (2008, methodology): “Another solution, as proposed in [33], is to scale the triangles of the deformed surface back to their original size and restitch the mesh by using the Poisson setup (15).”