Aerial Lifting: Neural Urban Semantic and Building Instance Lifting from Aerial Imagery

arXiv:2403.11812v1 Announce Type: new
Abstract: We present a neural radiance field method for urban-scale semantic and building-level instance segmentation from aerial images by lifting noisy 2D labels to 3D. This is a challenging problem due to two primary reasons. Firstly, objects in urban aerial images exhibit substantial variations in size, including buildings, cars, and roads, which pose a significant challenge for accurate 2D segmentation. Secondly, the 2D labels generated by existing segmentation methods suffer from the multi-view inconsistency problem, especially …

abstract aerial arxiv building cs.cv images instance labels neural radiance field objects scale segmentation semantic type urban