DPFM: Deep Partial Functional Maps

Attaiki, Souhaib; Pai, Gautam; Ovsjanikov, Maks

doi:10.48550/arxiv.2110.09994

Cited by 3 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, our approach offers a novel way to capture data to bridge the gap between synthetic simulation and real-world clothes. Applications include enhancing cloth physical simulations [40,63], facilitating the development of neural models for cloth dynamics [36,41,44] and non-rigid shape correspondence [2,14,22,23,33,45], designing precise interfaces for cloth manipulation by robots [8, 53, 72], ground-truth data to generative models for shape completion [7,17,31], and interpolation [19,21].…”

Section: Discussion Limitations and Future Workmentioning

confidence: 99%

Garment Avatars: Realistic Cloth Driving using Pattern Registration

Halimi¹,

Prada²,

Stuyck³

et al. 2022

Preprint

View full text Add to dashboard Cite

Section: Discussion Limitations and Future Workmentioning

confidence: 99%

Garment Avatars: Realistic Cloth Driving using Pattern Registration

Halimi¹,

Prada²,

Stuyck³

et al. 2022

Preprint

View full text Add to dashboard Cite

“…A potential solution for low-overlap scenarios is to expand the mutual information via data completion [38,75]. Rejecting outliers using the spectral methods [4,5] could also benefit non-rigid registration.…”

Section: Discussionmentioning

confidence: 99%

“…3DCODED [25] achieve non-rigid shape correspondence through latent code optimization. Functional mapbased [49] approaches have been proposed to produce dense non-rigid correspondence in [4,41,53].…”

Section: Non-rigid Correspondencementioning

confidence: 99%

Lepard: Learning partial point cloud matching in rigid and deformable scenes

Li¹,

Harada²

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Through some of the presented simulations, we will show that it can provide robustness to different types of density imbalances in structured and unstructured geometric data. But we shall also illustrate its potential to deal with partially observed data with curves and surfaces, which has been a recurrent and challenging issue for many different shape analysis models [22][23][24][25][26][27].…”

Section: Introductionmentioning

confidence: 99%

Weight metamorphosis of varifolds and the LDDMM-Fisher-Rao metric

Hsieh¹,

Charon²

2021

Preprint

View full text Add to dashboard Cite

This paper introduces and studies a metamorphosis framework for geometric measures known as varifolds, which extends the diffeomorphic registration model for objects such as curves, surfaces and measures by complementing diffeomorphic deformations with a transformation process on the varifold weights. We consider two classes of cost functionals to penalize those combined transformations, in particular the LDDMM-Fisher-Rao energy which, as we show, leads to a well-defined Riemannian metric on the space of varifolds with existence of corresponding geodesics. We further introduce relaxed formulations of the respective optimal control problems, study their well-posedness and derive optimality conditions for the solutions. From these, we propose a numerical approach to compute optimal metamorphoses between discrete varifolds and illustrate the interest of this model in the situation of partially missing data.

show abstract

DPFM: Deep Partial Functional Maps

Cited by 3 publications

References 0 publications

Garment Avatars: Realistic Cloth Driving using Pattern Registration

Garment Avatars: Realistic Cloth Driving using Pattern Registration

Lepard: Learning partial point cloud matching in rigid and deformable scenes

Weight metamorphosis of varifolds and the LDDMM-Fisher-Rao metric

Contact Info

Product

Resources

About