We present a novel dense semantic forecasting approach which is applicable to a variety of architectures and tasks. The approach consists of two modules. Feature-to-motion (F2M) module forecasts a dense deformation field which warps past features into their future positions. Feature-to-feature (F2F) module regresses the future features directly and is therefore able to account for emergent scenery. The compound F2MF approach decouples effects of motion from the effects of novelty in a task-agnostic manner. We aim to apply F2MF forecasting to the most subsampled and the most abstract representation of a desired single-frame model. Our implementations take advantage of deformable convolutions and pairwise correlation coefficients across neighbouring time instants. We perform experiments on three dense prediction tasks: semantic segmentation, instance-level segmentation, and panoptic segmentation. The results reveal state-of-the-art forecasting accuracy across all three modalities on the Cityscapes dataset.

翻译：我们提出了一个适用于各种结构和任务的新颖的密集语义预测方法,该方法由两个模块组成。地对地(F2M)模块预测一个密集的变形场,将过去的特征扭曲到它们未来的位置。地对地(F2F)模块将未来特征直接倒退,因此能够对突发的场景负责。复合F2MF方法将运动的影响与新事物的影响进行分解。我们的目标是将F2MF的预测应用到一个理想的单一框架模型中最次抽样和最抽象的表示中。我们的实施利用了可变形的共变异和相近时间的相联系数。我们在三种密集的预测任务上进行了实验:语义分解、实例分解和光谱分解。结果揭示了城景数据集所有三种模式的艺术预测准确性。