Data driven image models through continuous joint alignment

By Eric Learned-Miller. 2006

331 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

Learning Dense Correspondence via 3D-Guided Cycle Consistency (2016, methodology): “The classic like on work on Congealing [25, 16] uses sequential optimization to gradually lower the entropy of the intensity distribution of the entire image set by continuously warping each image via a parametric transformation (e.”
Tom-vs-Pete Classifiers and Identity-Preserving Alignment for Face Verification (2012, methodology): “One method often applied is Huang et al.'s [15] " funneling , " which extends the congealing method of Learned-Miller [20] to handle noisy, realworld images.”
GAN-Supervised Dense Visual Alignment (2021, methodology): “, [75,92]), with the seminal work of Congealing [31, 47] establishing unsupervised joint alignment as a research problem.”
Distribution fields for tracking (2012, methodology): “Congealing [15] has a large basin of attraction for alignment, since a collection of images can smooth the optimization landscape.”
Learning to Align from Scratch (2012, methodology): “, a training set), funneling [6,10] can be used to quickly align additional images, such as from a new test set.”
A Reproducible Evaluation of ANTs Similarity Metric Performance in Brain Image Registration (2010, methodology): “This is in contrast to methods such as congealing (Learned-Miller, 2006) or (Joshi et al., 2004) in that neither method explicitly optimizes the geometric component of the template.”
FlowWeb: Joint image set alignment by weaving consistent, pixel-wise correspondences (2015, background): “We compare our alignment performance with Congealing [23] (using SIFT), Collection Flow [18], DSP [21], and RASL [33].”
Deforming Autoencoders: Unsupervised Disentangling of Shape and Appearance (2018, background): “Despite this challenge several works in the previous decade aimed at learning shape/appearance factorizations in an unsupervised manner, exploring groupwise image alignment, [11,12,13,14].”
Unsupervised Joint Alignment of Complex Images (2007, unknown): “In the binary image case, a gray pixel is interpreted as being a mixture of underlying black and white “subpixels” [10].”
The Optimal Template Effect in Hippocampus Studies of Diseased Populations (2009, methodology): “SyGN is a contrast to methods such as congealing (Learned-Miller, 2006) or (Joshi et al., 2004) in that neither method explicitly represents ψ, the geometric component of the template.”
RASL: Robust alignment by sparse and low-rank decomposition for linearly correlated images (2010, methodology): “Figure 6 compares the performance of RASL (using Euclidean transformation G = E(2)) to that of [16] and [23].”
Labeled Faces in the Wild: A Survey (2016, methodology): “The method extends the congealing-style [56] method to handle real-world images.”