FlowFormer introduces a transformer architecture into optical flow estimation and achieves state-of-the-art performance. The core component of FlowFormer is the transformer-based cost-volume encoder. Inspired by the recent success of masked autoencoding (MAE) pretraining in unleashing transformers' capacity of encoding visual representation, we propose Masked Cost Volume Autoencoding (MCVA) to enhance FlowFormer by pretraining the cost-volume encoder with a novel MAE scheme. Firstly, we introduce a block-sharing masking strategy to prevent masked information leakage, as the cost maps of neighboring source pixels are highly correlated. Secondly, we propose a novel pre-text reconstruction task, which encourages the cost-volume encoder to aggregate long-range information and ensures pretraining-finetuning consistency. We also show how to modify the FlowFormer architecture to accommodate masks during pretraining. Pretrained with MCVA, FlowFormer++ ranks 1st among published methods on both Sintel and KITTI-2015 benchmarks. Specifically, FlowFormer++ achieves 1.07 and 1.94 average end-point error (AEPE) on the clean and final pass of Sintel benchmark, leading to 7.76\% and 7.18\% error reductions from FlowFormer. FlowFormer++ obtains 4.52 F1-all on the KITTI-2015 test set, improving FlowFormer by 0.16.

翻译：FlowFormer将Transformer架构引入光流估计，并取得了最先进的性能。其核心组件是基于Transformer的代价体编码器。受近期掩码自编码（MAE）预训练在释放Transformer编码视觉表示能力方面取得成功的启发，我们提出了掩码代价体自编码（MCVA），通过一种新颖的MAE方案对代价体编码器进行预训练来增强FlowFormer。首先，我们引入了一种块共享掩码策略，以阻止掩码信息泄露，因为相邻源像素的代价图高度相关。其次，我们提出了一种新颖的预文本重建任务，该任务激励代价体编码器聚合长程信息，并确保预训练与微调之间的一致性。我们还展示了如何在预训练期间修改FlowFormer架构以适配掩码。通过MCVA预训练，FlowFormer++在Sintel和KITTI-2015基准测试中均位列已发布方法的第一名。具体而言，FlowFormer++在Sintel基准测试的干净和最终通道上分别实现了1.07和1.94的平均端点误差（AEPE），相较于FlowFormer误差分别降低了7.76%和7.18%。FlowFormer++在KITTI-2015测试集上取得了4.52的F1-all值，相比FlowFormer提升了0.16。