Consistent Shape Maps via Semidefinite Programming

By Qi-Xing Huang, Leonidas J. Guibas. 2013

267 citations recorded by the source corpus.

Subfields: Computational Mechanics, 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 Computational Mechanics

In Computer Vision and Pattern Recognition

Citations in the corpus

Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks (2017, methodology): “More recently, higher-order cycle consistency has been used in structure from motion [56], 3D shape matching [19], co-segmentation [51], dense semantic alignment [59, 60], and depth estimation [12].”
SurfNet: Generating 3D Shape Surfaces Using Deep Residual Networks (2017, methodology): “We also wish to explore the proposed feedback mechanism to improve correspondences, or to use more sophisticated correspondence methods such as [14] to improve and increase the training set size.”
Sparse Representation for 3D Shape Estimation: A Convex Relaxation Approach (2015, background): “[56], [57]) and databases with rich annotations (e.”
FlowWeb: Joint image set alignment by weaving consistent, pixel-wise correspondences (2015, background): “Graph consistency: The idea of utilizing consistency constraints within a global graph structure has been applied to various vision and graphics problems, including cosegmentation [40, 41], structure from motion [47, 42], and shape matching [17].”
Unsupervised Visual Representation Learning by Graph-Based Consistent Constraints (2016, methodology): “Cycle consistency in a graph has been applied to various computer vision and graphics problems, including co-segmentation [28,29], structure from motion [30,31] and image matching [32,33].”
Solving Random Quadratic Systems of Equations Is Nearly as Easy as Solving Linear Systems (2015, background): “A concrete application of this flavor is a simple form of the fundamental alignment/matching problem [6, 15, 25].”
PointSIFT: A SIFT-like Network Module for 3D Point Cloud Semantic Segmentation (2018, background): “Further, functional map and cycle consistency [9, 10] helps build correspondence between shapes.”
Deep 3D human pose estimation: A review (2021, unknown): “This matching problem is formulated as a convex optimization problem with a cycle-consistency constraint and is solved by using the result of Huang and Guibas (2013).”
Community Detection in General Stochastic Block models: Fundamental Limits and Efficient Algorithms for Recovery (2015, methodology): “Finally, there are many interesting other models to investigate, such as the Censored Block Model [56], [51], [61], [57], [58], [59], [60], [62], the Labelled Block Model [68], [69] and many more.”
Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoning (2018, methodology): “Inspired by cycle consistency for learning correspondence [19, 66], Zhou et al. [65] train a CNN to predict correspondence between different objects of the same semantic class by utilizing CAD models.”
Recycle-GAN: Unsupervised Video Retargeting (2018, background): “Similar ideas have also found application in learning depth cues in an unsupervised manner [14], machine translation [47], shape correspondences [20], point-wise correspondences [51,52], or domain adaptation [18].”
Estimating image depth using shape collections (2014, methodology): “This is conceptually similar to state-of-the-art techniques in data-driven shape matching techniques [Kim et al. 2012a; Huang and Guibas 2013] to enforce consistency of correspondences along cycles to improve quality of isolated correspondences.”
Solving the multi-way matching problem by permutation synchronization (2013, methodology): “We thank Amit Singer for invaluable comments and for drawing our attention to [18].”
Learning Dense Correspondence via 3D-Guided Cycle Consistency (2016, methodology): “Instead, in this paper we utilize the concept of cycle consistency of correspondence flows [18, 40, 41] – the notion that the composition of flow fields for any circular path through the image set should have a zero combined flow.”
Learning Correspondence From the Cycle-Consistency of Time (2019, background): “Forward-backward consistency is a specific case of cycle-consistency, which has been widely applied as a learning objective for 3D shape matching [21], image alignment [87, 89, 88], depth estimation [86, 14, 84], and image-to-image translation [90, 4].”
Image Matching from Handcrafted to Deep Features: A Survey (2020, background): “Another body of work takes the initial (noisy) pairwisematching result as input, and aims to recover a globally consistent pairwise matching set (Kim et al. 2012; Pachauri et al. 2013; Huang and Guibas 2013; Chen et al. 2014; Zhou et al. 2015; Wang et al. 2018; Hu et al. 2018).”