IsoMatch: Creating Informative Grid Layouts

Fried, Ohad; DiVerdi, Stephen; Halber, Maciej; Sizikova, Elena; Finkelstein, Adam

doi:10.1111/cgf.12549

Cited by 40 publications

(42 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…"Kernelized sorting" [Quadrianto et al 2009] optimizes the Hilbert Schmidt Independence Criterion [Smola et al 2007], which coincides with the GW objective function after replacing geodesic distances with diffusion kernels. Fried et al [2015] apply this machinery to image layout problems. These methods are subject to the challenge of assembling many local constraints into one map.…”

Section: Related Workmentioning

confidence: 99%

Entropic metric alignment for correspondence problems

et al. 2016

View full text Add to dashboard Cite

Many shape and image processing tools rely on computation of correspondences between geometric domains. Efficient methods that stably extract "soft" matches in the presence of diverse geometric structures have proven to be valuable for shape retrieval and transfer of labels or semantic information. With these applications in mind, we present an algorithm for probabilistic correspondence that optimizes an entropy-regularized Gromov-Wasserstein (GW) objective. Built upon recent developments in numerical optimal transportation, our algorithm is compact, provably convergent, and applicable to any geometric domain expressible as a metric measure matrix. We provide comprehensive experiments illustrating the convergence and applicability of our algorithm to a variety of graphics tasks. Furthermore, we expand entropic GW correspondence to a framework for other matching problems, incorporating partial distance matrices, user guidance, shape exploration, symmetry detection, and joint analysis of more than two domains. These applications expand the scope of entropic GW correspondence to major shape analysis problems and are stable to distortion and noise.

show abstract

Section: Related Workmentioning

confidence: 99%

Entropic metric alignment for correspondence problems

et al. 2016

View full text Add to dashboard Cite

show abstract

“…To employ image arrangement with DS++ and DS*, we fix c in (44) such that d and d have the same mean [17]. Setup: We compare DS* with isomatch (using random swaps) [22] and DS++ [17] on various datasets (random colours, face images [49], and COCO [33]), where we used the RGB colour, MoFA facial expression parameters [49], and the average hue-saturation vector of each image as features, respectively. For the random colours experiment, in each run we uniformly sample random RGB values and then arrange the individual colours on the grid (i.e.…”

Section: Image Arrangementmentioning

confidence: 99%

DS: Tighter Lifting-Free Convex Relaxations for Quadratic Matching Problems

Bernard

Theobalt

Moeller

2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

In this work we study convex relaxations of quadratic optimisation problems over permutation matrices. While existing semidefinite programming approaches can achieve remarkably tight relaxations, they have the strong disadvantage that they lift the original n×n-dimensional variable to an n 2 ×n 2 -dimensional variable, which limits their practical applicability. In contrast, here we present a lifting-free convex relaxation that is provably at least as tight as existing (lifting-free) convex relaxations. We demonstrate experimentally that our approach is superior to existing convex and non-convex methods for various problems, including image arrangement and multi-graph matching. DS* (our)SDP spectral 6 8 10 12

show abstract

“…A popular solution for this problem is the "kernelized sorting" technique introduced in [33], in which the authors utilize kernels and a learned centering matrix to make distances in X and Y comparable. More recently, Fried et al elaborate a method to match a set of objects with a layout called IsoMatch [34]. Although our method is similar to IsoMatch in a spirit, the goals of the two methods are different.…”

Section: Object Arrangement and Browsingmentioning

confidence: 99%

Color Orchestra: Ordering Color Palettes for Interpolation and Prediction

Phan

Chan

2018

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

Abstract-Color theme or color palette can deeply influence the quality and the feeling of a photograph or a graphical design. Although color palettes may come from different sources such as online crowd-sourcing, photographs and graphical designs, in this paper, we consider color palettes extracted from fine art collections, which we believe to be an abundant source of stylistic and unique color themes. We aim to capture color styles embedded in these collections by means of statistical models and to build practical applications upon these models. As artists often use their personal color themes in their paintings, making these palettes appear frequently in the dataset, we employed density estimation to capture the characteristics of palette data. Via density estimation, we carried out various predictions and interpolations on palettes, which led to promising applications such as photo-style exploration, real-time color suggestion, and enriched photo recolorization. It was, however, challenging to apply density estimation to palette data as palettes often come as unordered sets of colors, which make it difficult to use conventional metrics on them. To this end, we developed a divide-and-conquer sorting algorithm to rearrange the colors in the palettes in a coherent order, which allows meaningful interpolation between color palettes. To confirm the performance of our model, we also conducted quantitative experiments on datasets of digitized paintings collected from the Internet and received favorable results.

show abstract

IsoMatch: Creating Informative Grid Layouts

Cited by 40 publications

References 28 publications

Entropic metric alignment for correspondence problems

Entropic metric alignment for correspondence problems

DS: Tighter Lifting-Free Convex Relaxations for Quadratic Matching Problems

Color Orchestra: Ordering Color Palettes for Interpolation and Prediction

Contact Info

Product

Resources

About