Coarse‐to‐Fine Combinatorial Matching for Dense Isometric Shape Correspondence

Sahillioğlu, Yusuf; Yemez, Y.

doi:10.1111/j.1467-8659.2011.02020.x

Cited by 66 publications

(60 citation statements)

References 28 publications

(45 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…method AE (cm) worst AE 10cm-recall GMDS [8] 28.98 91.84 0.300 Möbius [24] 14.99 80.40 0.614 BIM [19] 13.60 83.90 0.658 C2F [36] 23 Accuracy on inter-subject pairs Figure 4. Evaluation on the FAUST dataset.…”

Section: Resultsmentioning

confidence: 99%

“…We compare the presented approach to a large number of prior methods for which we could obtain implementations online or by contacting the authors: GMDS [8], Möbius voting [24], blended intrinsic maps (BIM) [19], coarse-tofine matching (C2F) [36], the EM algorithm [37], coarse-tofine matching with symmetric flips (C2FSym) [38], sparse modeling (SM) [30], elastic net constraints (ENC) [34], and random forests (RF) [33]. Each method is evaluated on all intra-subject pairs and all inter-subject pairs.…”

Section: Methodsmentioning

confidence: 99%

“…While multiresolution schemes and various search techniques have been proposed, GMDS is generally not considered viable without a good initialization [7,31,36,38]. Our work expresses the GMDS objective as a Markov random field (MRF) and leverages powerful methods developed for MRF optimization over the last decade.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Robust Nonrigid Registration by Convex Optimization

Chen

Koltun

2015

2015 IEEE International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

We present an approach to nonrigid registration of 3D surfaces. We cast isometric embedding as MRF optimization and apply efficient global optimization algorithms based on linear programming relaxations. The Markov random field perspective suggests a natural connection with robust statistics and motivates robust forms of the intrinsic distortion functional. Our approach outperforms a large body of prior work by a significant margin, increasing registration precision on real data by a factor of 3.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Robust Nonrigid Registration by Convex Optimization

Chen

Koltun

2015

2015 IEEE International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

show abstract

“…In this set of experiments we compare with the state of the art techniques in (dense) non-rigid shape matching, namely the functional maps pipeline [14], blended intrinsic maps (BIM) [8], and the coarse-to-fine combinatorial approach of [19]. We perform these comparisons on the TOSCA high-resolution dataset [4].…”

Section: Comparison With Dense Methodsmentioning

confidence: 99%

Dense Non-rigid Shape Correspondence Using Random Forests

Rodolà¹,

Bulò²,

Windheuser³

et al. 2014

2014 IEEE Conference on Computer Vision and Pattern Recognition

130

114

View full text Add to dashboard Cite

We propose a shape matching method that produces dense correspondences tuned to a specific class of shapes and deformations. In a scenario where this class is represented by a small set of example shapes, the proposed method learns a shape descriptor capturing the variability of the deformations in the given class. The approach enables the wave kernel signature to extend the class of recognized deformations from near isometries to the deformations appearing in the example set by means of a random forest classifier. With the help of the introduced spatial regularization, the proposed method achieves significant improvements over the baseline approach and obtains stateof-the-art results while keeping short computation times.

show abstract

“…Perhaps the most common model in the context of intrinsic (i.e., not relying on vertex positions and not assuming approximate alignment) approaches is approximate isometries, introduced by Bronstein et al [5] and Mémoli [21]. This model has been used by a large number of methods, (e.g., [13,33,23,28,22] among many others) that all assume that the sought correspondences must approximately preserve pairwise geodesic distances. Another set of approaches is based on a more relaxed model, conformal mappings, used by, e.g., [19,17] where only angles are assumed to be preserved.…”

Section: Related Workmentioning

confidence: 99%

Supervised Descriptor Learning for Non-Rigid Shape Matching

Corman

Ovsjanikov

Chambolle

2015

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. We present a novel method for computing correspondences between pairs of non-rigid shapes. Unlike the majority of existing techniques that assume a deformation model, such as intrinsic isometries, a priori and use a pre-defined set of point or part descriptors, we consider the problem of learning a correspondence model given a collection of reference pairs with known mappings between them. Our formulation is purely intrinsic and does not rely on a consistent parametrization or spatial positions of vertices on the shapes. Instead, we consider the problem of finding the optimal set of descriptors that can be jointly used to reproduce the given reference maps. We show how this problem can be formalized and solved for efficiently by using the recently proposed functional maps framework. Moreover, we demonstrate how to extract the functional subspaces that can be mapped reliably across shapes. This gives us a way to not only obtain better functional correspondences, but also to associate a confidence value to the different parts of the mappings. We demonstrate the efficiency and usefulness of the proposed approach on a variety of challenging shape matching tasks.

show abstract

Coarse‐to‐Fine Combinatorial Matching for Dense Isometric Shape Correspondence

Abstract: Abstract

Cited by 66 publications

References 28 publications

Robust Nonrigid Registration by Convex Optimization

Robust Nonrigid Registration by Convex Optimization

Dense Non-rigid Shape Correspondence Using Random Forests

Supervised Descriptor Learning for Non-Rigid Shape Matching

Contact Info

Product

Resources

About