论文标题
dyna-dm：动态对象感知的自我监督的单眼图
Dyna-DM: Dynamic Object-aware Self-supervised Monocular Depth Maps
论文作者
论文摘要
近年来，由于它在机器人技术和自主驾驶中的应用，自我监督的单眼深度估计一直是一项激烈研究的主题。最近的许多工作都集中在通过提高体系结构复杂性来改善深度估计。本文表明，也可以通过改善学习过程而不是提高模型复杂性来实现最先进的绩效。更具体地说，我们建议（i）训练时（i）忽略小型潜在动态对象，以及（ii）采用基于外观的方法分别估计对象构成真正动态对象的姿势。我们证明，这些简化将GPU存储器的使用量减少了29％，并导致定性和定量改进的深度图。该代码可在https://github.com/kieran514/dyna-dm上找到。
Self-supervised monocular depth estimation has been a subject of intense study in recent years, because of its applications in robotics and autonomous driving. Much of the recent work focuses on improving depth estimation by increasing architecture complexity. This paper shows that state-of-the-art performance can also be achieved by improving the learning process rather than increasing model complexity. More specifically, we propose (i) disregarding small potentially dynamic objects when training, and (ii) employing an appearance-based approach to separately estimate object pose for truly dynamic objects. We demonstrate that these simplifications reduce GPU memory usage by 29% and result in qualitatively and quantitatively improved depth maps. The code is available at https://github.com/kieran514/Dyna-DM.
