Digital image warping

By George Wolberg. 1990

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

Generative Visual Manipulation on the Natural Image Manifold (2016, methodology): “Traditional morphing methods [11] combine an intensity blend with a geometric warp that requires a dense correspondence.”
Rewriting a Deep Generative Model (2020, background): “Common operations include color transfer [65,53], image deformation [67,75], object cloning [62,11], and patch-based image synthesis [20,5,29].”
Quantitative evaluation of convolution-based methods for medical image interpolation (2001, methodology): “Wolberg [ 61 ]. In principle, the additional errors due to the spatial quantization of a kernel can be reduced to any level simply by increasing the density of kernel samples.”
Local seismic attributes (2007, background): “The term " image warping " comes from medical imaging (Wolberg, 1990) and refers, in this case, to squeezing the SS image to PP reflection time to make the two images display in the same coordinate system.”
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].”
Learned Image Downscaling for Upscaling Using Content Adaptive Resampler (2019, methodology): “Those methods are based on linear ﬁlters [10], where the HR image is ﬁrstly convolved with a low-pass kernel to push frequency components of the image below the Nyquist frequency [11], then being sub-sampled into target size.”
Regenerative morphing (2010, methodology): “Traditional morphing methods [18, 3, 6, 11, 15] combine a geometric warp and an intensity blend.”
Robust multiresolution alignment of MRI brain volumes (2000, methodology): “[18] using a simplex method, and then used the mean and variance of the central (main lobe) Gaussian to contrast equalize the two volumes.”
Female faces and bodies: N-dimensional feature space and attractiveness. (2002, methodology): “A computer program for the size standardization of the faces and figures was developed following Bookstein (1997) and Wolberg (1990) using a simplified version of the procrustes approach.”
On Benchmarking Optical Flow (2001, methodology): “We follow the development given by Wolberg [21].”
Hallucinating faces (2000, background): “The class of images of human faces is a relatively small subset.”
Image-Guided Robotic Flexible Needle Steering (2007, methodology): “We used fourth-degree bipolynomials which correct most of the fluoroscopic image distortions [17].”
Generalizing the Nonlocal-Means to Super-Resolution Reconstruction (2009, methodology): “As there are no published methods that perform super resolution on such general sequences, the comparison we provide is to a single image up-sampling using the Lanczos algorithm [45], [46] that effectively approximates the Sinc interpolation.”
View morphing (1996, methodology): “In this paper, the term image morphing refers specifically to methods that use linear interpolation to compute feature positions in in-between images, including [15, 1, 8].”