We present a new regularization method to find structure in point clouds corrupted by outliers. The method organizes points into a graph structure, and uses isoperimetric inequalities to craft a loss function that is minimized alternatingly to identify outliers, and annihilate their effect. It can operate in the presence of large amounts of outliers, and inlier noise. The approach is applicable to both low-dimensional point clouds, such as those obtained from stereo or structured light, as well as high-dimensional ones.

Finding Structure in Point Cloud Data with the Robust Isoperimetric Loss / Deutsch, S; Masi, I; Soatto, S. - (2019). (Intervento presentato al convegno International Conference on Scale Space and Variational Methods in Computer Vision (SSVM) tenutosi a Hofgeismar).

Finding Structure in Point Cloud Data with the Robust Isoperimetric Loss

Masi I;
2019

Abstract

We present a new regularization method to find structure in point clouds corrupted by outliers. The method organizes points into a graph structure, and uses isoperimetric inequalities to craft a loss function that is minimized alternatingly to identify outliers, and annihilate their effect. It can operate in the presence of large amounts of outliers, and inlier noise. The approach is applicable to both low-dimensional point clouds, such as those obtained from stereo or structured light, as well as high-dimensional ones.
2019
International Conference on Scale Space and Variational Methods in Computer Vision (SSVM)
denosing methods
04 Pubblicazione in atti di convegno::04b Atto di convegno in volume
Finding Structure in Point Cloud Data with the Robust Isoperimetric Loss / Deutsch, S; Masi, I; Soatto, S. - (2019). (Intervento presentato al convegno International Conference on Scale Space and Variational Methods in Computer Vision (SSVM) tenutosi a Hofgeismar).
File allegati a questo prodotto
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11573/1458924
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? 1
social impact