Urban expansion models (UEMs) help unfold the mechanism, future pathways, and relevant repercussions of urban landscape dynamics. Although a plethora of UEMs have been developed, the field of open-access modeling platform for urban expansion simulation still presents gaps in terms of representing urban development events, regulating multilevel urban morphologies, and reflecting underlying regularities of physical urban growth. This study develops an open-access Multiengine Urban Expansion Simulation (MUSE) platform together with software that addresses some of these limitations. MUSE employs patch-based concepts and different patch generation engines to represent urban development events of distinctive types, enabling control over spatial morphology at landscape, class and patch levels. Moreover, MUSE incorporates two general regularities on urban development waves and urban diffusion and coalescence to govern physical urban expansion processes. Experiments in two cities examine MUSE’s ability in simulating realistic urban dynamics, and a series of synthetic experiments verify the operational behavior of the patch generation engines. These experiments show that MUSE can simulate a range of urban expansion types, including infill, edge growth and leapfrog expansion, and various morphologies, such as aggregated, sprawl, fragmented and compact. MUSE can empower practitioners to better project, analyze and understand complex urbanization dynamics.

In this work, we tackle the task of estimating the 6D pose of an object from point cloud data. While recent learning-based approaches have shown remarkable success on synthetic datasets, we have observed them to fail in the presence of real-world data. We investigate the root causes of these failures and identify two main challenges: The sensitivity of the widely-used SVD-based loss function to the range of rotation between the two point clouds, and the difference in feature distributions between the source and target point clouds. We address the first challenge by introducing a directly supervised loss function that does not utilize the SVD operation. To tackle the second, we introduce a new normalization strategy, Match Normalization. Our two contributions are general and can be applied to many existing learning-based 3D object registration frameworks, which we illustrate by implementing them in two of them, DCP and IDAM. Our experiments on the real-scene TUD-L Hodan et al. 2018, LINEMOD Hinterstoisser et al. 2012 and Occluded-LINEMOD Brachmann et al. 2014 datasets evidence the benefits of our strategies. They allow for the first-time learning-based 3D object registration methods to achieve meaningful results on real-world data. We therefore expect them to be key to the future developments of point cloud registration methods.