Self-supervised methods play an increasingly important role in monocular
depth estimation due to their great potential and low annotation cost. To close
the gap with supervised methods, recent works take advantage of extra
constraints, e.g., semantic segmentation. However, these methods will
inevitably increase the burden on the model. In this paper, we show theoretical
and empirical evidence that the potential capacity of self-supervised monocular
depth estimation can be excavated without increasing this cost. In particular,
we propose (1) a novel data augmentation approach called data grafting, which
forces the model to explore more cues to infer depth besides the vertical image
position, (2) an exploratory self-distillation loss, which is supervised by the
self-distillation label generated by our new post-processing method - selective
post-processing, and (3) the full-scale network, designed to endow the encoder
with the specialization of depth estimation task and enhance the
representational power of the model. Extensive experiments show that our
contributions can bring significant performance improvement to the baseline
with even less computational overhead, and our model, named EPCDepth, surpasses
the previous state-of-the-art methods even those supervised by additional
constraints.

该研究提出一种新的数据增强方法（data grafting）、探索性自蒸馏损失函数（exploratory self-distillation loss）、和全尺寸卷积神经网络，以提高自监督单目深度估计的表示能力和性能表现，实验结果表明该模型 EPCDepth 在更少的计算量下超越了之前的最新优秀模型。