HD-VoxelFlex: Flexible High-Definition Voxel Grid Representation

Igor Vozniak, Pavel Astreika, Philipp Müller, Nils Lipp, Christian Müller, Philipp Slusallek

Abstract: Voxel grids are an effective means to represent 3D data, as they accurately preserve spatial relations. However, the inherent sparseness of voxel grid representations leads to significant memory consumption in deep learning architectures, in particular for high-resolution (HD) inputs. As a result, current state-of-the-art approaches to the reconstruction of 3D data tend to avoid voxel grid inputs. In this work, we propose HD-VoxelFlex, a novel 3D CNN architecture that can be flexibly applied to HD voxel grids with only moderate increase in training parameters and memory consumption. HD-VoxelFlex introduces three architectural novelties. First, to improve the models’ generalizability, we introduce a random shuffling layer. Second, to reduce information loss, we introduce a novel reducing skip connection layer. Third, to improve modelling of local structure that is crucial for HD inputs, we incorporate a kNN distance mask as input. We combine these novelties with a “bag of tricks” iden