Image deformation using moving least squares

By Scott Schaefer, T. McPhail, Joe D. Warren. 2006

839 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

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

In Computer Vision and Pattern Recognition

Citations in the corpus

An Integrated Micro- and Macroarchitectural Analysis of the Drosophila Brain by Computer-Assisted Serial Section Electron Microscopy (2010, methodology): “individual section using the Moving Least Squared method [33]”
Rewriting a Deep Generative Model (2020, methodology): “Common operations include color transfer [65,53], image deformation [67,75], object cloning [62,11], and patch-based image synthesis [20,5,29].”
Local Affine Multidimensional Projection (2011, methodology): “The minimization problem (1) is similar to that employed in “asrigid-as-possible” image deformation [ 30 ].”
A system for retargeting of streaming video (2009, methodology): “Similar concepts have been employed for image editing [Schaefer et al. 2006] or 3D mesh resizing [Kraevoy et al. 2008].”
Automatic Metallic Surface Defect Detection and Recognition with Convolutional Neural Networks (2018, methodology): “In order to train a suitable network, some data augmentation strategies were introduced, mainly including random rotation, translation, zoom, shear, and elastic transformation [43].”
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.”
Sketch-a-Net: A Deep Neural Network that Beats Humans (2016, methodology): “4a), we then employ the moving least squares (MLSs) algorithm (Schaefer et al. 2006) to get new position of all points”
A Unified Framework for Street-View Panorama Stitching (2016, methodology): “The work in [34] provided an image deformation method based on moving least squares [35] using various classes of linear functions including affine, similarity and rigid transformations.”
EditGAN: High-Precision Semantic Image Editing (2021, background): “Image Editing has a long history in computer vision and graphics, as well as machine learning [29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 18, 11, 28, 41, 42, 16].”
Surface defect saliency of magnetic tile (2018, methodology): “Since data augmentation on a single small dataset may causes overfitting, to prevent the model from overfitting, an distinct image deformation method using Moving Least Square [26] is introduced.”
Neural best-buddies (2018, methodology): “This is done by interpolating our correspondences with Moving Least Squares (MLS) [Schaefer et al. 2006] warping field, which is described in more detail in Section 5.1.”
Map-based exploration of intrinsic shape differences and variability (2013, methodology): “[Schaefer et al. 2006; Ben-Chen et al. 2009], among others), is to consider the local affine distortion introduced by the map at every point on the shape, e.”
Sketch Me That Shoe (2016, methodology): “Inspired by this, we employ the Moving Least Squares algorithm [24] for stroke deformation.”
As-Projective-As-Possible Image Stitching with Moving DLT (2013, methodology): “Following [14], we partition the source image I into a grid of C1×C2 cells.”
Synthesizing Training Images for Boosting Human 3D Pose Estimation (2016, methodology): “We want the warping to be smooth for minimizing artifacts, and we achieve this by applying MLS image deformation [35].”