Abstract
Semantic scene completion, also known as semantic occupancy prediction, can provide dense geometric and semantic information for autonomous vehicles, which attracts the increasing attention of both academia and industry. Unfortunately, existing methods usually formulate this task as a voxel-wise classification problem and treat each voxel equally in 3D space during training. As the hard voxels have not been paid enough attention, the performance in some challenging regions is limited. The 3D dense space typically contains a large number of empty voxels, which are easy to learn but require amounts of computation due to handling all the voxels uniformly for the existing models. Furthermore, the voxels in the boundary region are more challenging to differentiate than those in the interior. In this paper, we propose HASSC approach to train the semantic scene completion model with hardness-aware design. The global hardness from the network optimization process is defined for dynamical hard voxel selection. Then, the local hardness with geometric anisotropy is adopted for voxel-wise refinement. Besides, self-distillation strategy is introduced to make training process stable and consistent. Extensive experiments show that our HASSC scheme can effectively promote the accuracy of the baseline model without incurring the extra inference cost. Source code is available at: this https URL.
Abstract (translated)
语义场景完成（也称为语义占用预测），可以为自动驾驶车辆提供丰富的几何和语义信息，这吸引了学术界和产业界越来越多的关注。然而，现有的方法通常将此任务表示为体素级的分类问题，并且在训练过程中对每个体素同等对待3D空间。由于对难于学习的难于体素没有给予足够的关注，因此在一些具有挑战性的区域，性能有限。通常，3D密集空间包含大量空体素，这些体素容易学习，但由于处理所有体素的方式相同，需要大量的计算。此外，边界区域内的体素比内部更难区分。在本文中，我们提出了带有硬化设计的语义场景完成模型来训练具有硬化设计的模型。对网络优化过程的全局硬度定义为动态选择难以学习的体素。然后，采用局部硬度与几何变形来对体素进行逐个细化。此外，还引入了自蒸馏策略来使训练过程稳定和一致。大量实验证明，我们的HASSC方案可以在不产生额外推理成本的情况下有效提高基线模型的准确性。代码可在此处下载：https://这个链接。
URL
https://arxiv.org/abs/2404.11958
