Region-Based Correspondence Between 3D Shapes via Spatially Smooth Biclustering

Denitto, Matteo; Melzi, Simone; Bicego, Manuele; Castellani, Umberto; Farinelli, Alessandro; Figueiredo, Mário A. T.; Kleiman, Yanir; Ovsjanikov, Maks

doi:10.1109/iccv.2017.457

Cited by 6 publications

(3 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The desired region should be handy to retrieve on unseen data, and informative about the geometry and the details that characterize the objects of the class. For general objects, such as airplanes, some well-established segmentation approaches could solve this task both in a data-driven fashion [18,37] or with more classical algorithms [9,19]. This is possible also in more articulated cases like humans, identifying local regions like the head extractor proposed in [24].…”

Section: Methodsmentioning

confidence: 99%

Localized Shape Modelling with Global Coherence: An Inverse Spectral Approach

Pegoraro¹,

Melzi²,

Castellani³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

In this work, we present a new learning-based pipeline for the generation of 3D shapes. We build our method on top of recent advances on the so called shape-from-spectrum paradigm, which aims at recovering the full 3D geometric structure of an object only from the eigenvalues of its Laplacian operator. In designing our learning strategy, we consider the spectrum as a natural and ready to use representation to encode variability of the shapes. Therefore, we propose a simple decoder-only architecture that directly maps spectra to 3D embeddings; in particular, we combine information from global and local spectra, the latter being obtained from localized variants of the manifold Laplacian. This combination captures the relations between the full shape and its local parts, leading to more accurate generation of geometric details and an improved semantic control in shape synthesis and novel editing applications. Our results confirm the improvement of the proposed approach in comparison to existing and alternative methods.

show abstract

Section: Methodsmentioning

confidence: 99%

Localized Shape Modelling with Global Coherence: An Inverse Spectral Approach

Pegoraro¹,

Melzi²,

Castellani³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…This matching method may also fall when there are highly symmetrical and drastically deformed clouds, such as human bodies rigged face to face. In the future, we will study more robust region matching methods or try other types of region corresponding methods [55,56]. Our current method is also slow without accelerating the optimization.…”

Section: : Statistical Comparisons Of the Varying Matches After Apply...mentioning

confidence: 99%

Automatic Extraction of the Sparse Prior Correspondences for Non-Rigid Point Cloud Registration

Zhu¹,

Tian²,

Ye³

et al. 2023

Computer Modeling in Engineering &Amp; Sciences

View full text Add to dashboard Cite

Non-rigid registration of point clouds is still far from stable, especially for the largely deformed one. Sparse initial correspondences are often adopted to facilitate the process. However, there are few studies on how to build them automatically. Therefore, in this paper, we propose a robust method to compute such priors automatically, where a global and local combined strategy is adopted. These priors in different degrees of deformation are obtained by the locally geometrical-consistent point matches from the globally structural-consistent region correspondences. To further utilize the matches, this paper also proposes a novel registration method based on the Coherent Point Drift framework. This method takes both the spatial proximity and local structural consistency of the priors as supervision of the registration process and thus obtains a robust alignment for clouds with significantly different deformations. Qualitative and quantitative experiments demonstrate the advantages of the proposed method.

show abstract

“…Other works have been devoted to the selection of appropriate probe functions used to guide the computation of functional maps. Axiomatic descriptors such as HKS, WKS or SHOT [51,3,56] are widely used as probe functions together with supervised information such as segments and landmarks [17,11]. More recently, an optimisation-based strategy has been proposed to compute optimal relative weights of probe functions [10], while a set of five automatically estimated stable landmarks has been used as probe functions for functional maps on human shapes in [32].…”

Section: Functional Mapsmentioning

confidence: 99%

Correspondence Learning via Linearly-invariant Embedding

Marin¹,

Rakotosaona²,

Melzi³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

In this paper, we propose a fully differentiable pipeline for estimating accurate dense correspondences between 3D point clouds. The proposed pipeline is an extension and a generalization of the functional maps framework. However, instead of using the Laplace-Beltrami eigenfunctions as done in virtually all previous works in this domain, we demonstrate that learning the basis from data can both improve robustness and lead to better accuracy in challenging settings. We interpret the basis as a learned embedding into a higher dimensional space. Following the functional map paradigm the optimal transformation in this embedding space must be linear and we propose a separate architecture aimed at estimating the transformation by learning optimal descriptor functions. This leads to the first end-to-end trainable functional map-based correspondence approach in which both the basis and the descriptors are learned from data. Interestingly, we also observe that learning a canonical embedding leads to worse results, suggesting that leaving an extra linear degree of freedom to the embedding network gives it more robustness, thereby also shedding light onto the success of previous methods. Finally, we demonstrate that our approach achieves state-of-the-art results in challenging non-rigid 3D point cloud correspondence applications. * denotes equal contribution.34th Conference on Neural Information Processing Systems (NeurIPS 2020),

show abstract

Region-Based Correspondence Between 3D Shapes via Spatially Smooth Biclustering

Cited by 6 publications

References 43 publications

Localized Shape Modelling with Global Coherence: An Inverse Spectral Approach

Localized Shape Modelling with Global Coherence: An Inverse Spectral Approach

Automatic Extraction of the Sparse Prior Correspondences for Non-Rigid Point Cloud Registration

Correspondence Learning via Linearly-invariant Embedding

Contact Info

Product

Resources

About