We propose MAMo, a novel memory and attention frame-work for monocular video depth estimation. MAMo can augment and improve any single-image depth estimation networks into video depth estimation models, enabling them to take advantage of the temporal information to predict more accurate depth. In MAMo, we augment model with memory which aids the depth prediction as the model streams through the video. Specifically, the memory stores learned visual and displacement tokens of the previous time instances. This allows the depth network to cross-reference relevant features from the past when predicting depth on the current frame. We introduce a novel scheme to continuously update the memory, optimizing it to keep tokens that correspond with both the past and the present visual information. We adopt attention-based approach to process memory features where we first learn the spatio-temporal relation among the resultant visual and displacement memory tokens using self-attention module. Further, the output features of self-attention are aggregated with the current visual features through cross-attention. The cross-attended features are finally given to a decoder to predict depth on the current frame. Through extensive experiments on several benchmarks, including KITTI, NYU-Depth V2, and DDAD, we show that MAMo consistently improves monocular depth estimation networks and sets new state-of-the-art (SOTA) accuracy. Notably, our MAMo video depth estimation provides higher accuracy with lower latency, when omparing to SOTA cost-volume-based video depth models.

翻译：我们提出MAMo，一种面向单目视频深度估计的新型记忆与注意力框架。MAMo能够增强并改进任何单图像深度估计网络，将其转化为视频深度估计模型，使其利用时序信息预测更精确的深度。在MAMo中，我们通过记忆增强模型，使模型在视频流处理过程中能够借助记忆辅助深度预测。具体而言，记忆存储了前一时刻学习到的视觉与位移标记，使得深度网络在预测当前帧深度时，可以交叉参考来自过去的关联特征。我们提出一种持续更新记忆的新方案，通过优化使记忆保留与过去及当前视觉信息均对应的标记。采用基于注意力的方法处理记忆特征：首先利用自注意力模块学习所得视觉与位移记忆标记的时空关系，随后通过交叉注意力将自注意力输出特征与当前视觉特征进行聚合。最终将交叉注意力特征输入解码器，预测当前帧深度。通过在KITTI、NYU-Depth V2和DDAD等多个基准上的大量实验证明，MAMo能够持续提升单目深度估计网络性能，并创下新的最优（SOTA）精度。值得注意的是，与基于代价体积的SOTA视频深度模型相比，我们的MAMo视频深度估计在更低延迟下实现了更高精度。