Learnable Earth Parser: Discovering 3D Prototypes in Aerial Scans

arXiv:2304.09704v2 Announce Type: replace
Abstract: We propose an unsupervised method for parsing large 3D scans of real-world scenes with easily-interpretable shapes. This work aims to provide a practical tool for analyzing 3D scenes in the context of aerial surveying and mapping, without the need for user annotations. Our approach is based on a probabilistic reconstruction model that decomposes an input 3D point cloud into a small set of learned prototypical 3D shapes. The resulting reconstruction is visually interpretable and can …

aerial arxiv cs.cv earth scans type