SAL: Sign Agnostic Learning of Shapes From Raw Data

Matan Atzmon, Yaron Lipman

Research output: Contribution to journalConference article


Recently, neural networks have been used as implicit representations for surface reconstruction, modelling, learning, and generation. So far, training neural networks to be implicit representations of surfaces required training data sampled from a ground-truth signed implicit functions such as signed distance or occupancy functions, which are notoriously hard to compute. In this paper we introduce Sign Agnostic Learning (SAL), a deep learning approach for learning implicit shape representations directly from raw, unsigned geometric data, such as point clouds and triangle soups. We have tested SAL on the challenging problem of surface reconstruction from an un-oriented point cloud, as well as end-to-end human shape space learning directly from raw scans dataset, and achieved state of the art reconstructions compared to current approaches. We believe SAL opens the door to many geometric deep learning applications with real-world data, alleviating the usual painstaking, often manual pre-process.
Original languageEnglish
Article number9156833
Pages (from-to)2562-2571
Number of pages10
Journal2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
StatePublished - Jun 2020


Dive into the research topics of 'SAL: Sign Agnostic Learning of Shapes From Raw Data'. Together they form a unique fingerprint.

Cite this