Unsupervised Occupancy Learning from Sparse Point Cloud

arXiv:2404.02759v1 Announce Type: cross
Abstract: Implicit Neural Representations have gained prominence as a powerful framework for capturing complex data modalities, encompassing a wide range from 3D shapes to images and audio. Within the realm of 3D shape representation, Neural Signed Distance Functions (SDF) have demonstrated remarkable potential in faithfully encoding intricate shape geometry. However, learning SDFs from 3D point clouds in the absence of ground truth supervision remains a very challenging task. In this paper, we propose a method to …

abstract arxiv audio cloud cs.ai cs.cv cs.gr cs.lg data encoding framework functions geometry images implicit neural representations realm representation type unsupervised