Online stereo adaptation tackles the domain shift problem, caused by different environments between synthetic (training) and real (test) datasets, to promptly adapt stereo models in dynamic real-world applications such as autonomous driving. However, previous methods often fail to counteract particular regions related to dynamic objects with more severe environmental changes. To mitigate this issue, we propose to incorporate an auxiliary point-selective network into a meta-learning framework, called PointFix, to provide a robust initialization of stereo models for online stereo adaptation. In a nutshell, our auxiliary network learns to fix local variants intensively by effectively back-propagating local information through the meta-gradient for the robust initialization of the baseline model. This network is model-agnostic, so can be used in any kind of architectures in a plug-and-play manner. We conduct extensive experiments to verify the effectiveness of our method under three adaptation settings such as short-, mid-, and long-term sequences. Experimental results show that the proper initialization of the base stereo model by the auxiliary network enables our learning paradigm to achieve state-of-the-art performance at inference.
翻译:在线立体适应解决了由合成(培训)和真实(测试)数据集之间不同环境造成的域变问题,以便在动态现实世界应用中迅速调整立体模型,如自主驱动。然而,以往的方法往往无法抵消与环境变化更为严重的动态物体有关的特定区域。为缓解这一问题,我们提议将一个辅助点选择性网络纳入一个称为PointFix的元学习框架,以便为在线立体适应提供一种稳健的立体模型初始化。 在一个综合体中,我们的辅助网络学会通过对基线模型的稳健初始化的元阶段有效反向传播本地信息,从而快速修正本地变体。这个网络是模型不可知性,因此可以以插接和游戏的方式用于任何类型的结构。我们进行了广泛的实验,以核实我们在三个适应环境中的方法的有效性,例如短、中、长期序列。实验结果显示,辅助网络对基础立体模型的正确初始化使得我们的学习模式能够实现推断的状态性能。