For many vision tasks, utilizing pre-trained features results in improved performance and consistently benefits from the rapid advancement of pre-training technologies. However, in the field of stereo matching, the use of pre-trained features has not been extensively researched. In this paper, we present the first systematical exploration into the utilization of pre-trained features for stereo matching. To provide flexible employment for any combination of pre-trained backbones and stereo matching networks, we develop the deformable neck (DN) that decouples the network architectures of these two components. The core idea of DN is to utilize the deformable attention mechanism to iteratively fuse pre-trained features from shallow to deep layers. Empirically, our exploration reveals the crucial factors that influence using pre-trained features for stereo matching. We further investigate the role of instance-level information of pre-trained features, demonstrating it benefits stereo matching while can be suppressed during convolution-based feature fusion. Built on the attention mechanism, the proposed DN module effectively utilizes the instance-level information in pre-trained features. Besides, we provide an understanding of the efficiency-accuracy tradeoff, concluding that using pre-trained features can also be a good alternative with efficiency consideration.

对于许多视觉任务，利用预训练的特征可以提高性能，并持续受益于预训练技术的快速发展。然而，在立体匹配领域，预训练特征的使用尚未得到广泛研究。在本文中，我们首次系统地探索了利用预训练特征进行立体匹配。为了为预训练主干和立体匹配网络的任意组合提供灵活的使用，我们开发了可变形颈部（DN），它将这两个组件的网络架构解耦。 DN的核心思想是利用可变形注意力机制从浅层到深层迭代融合预训练的特征。根据经验，我们的探索揭示了影响使用预训练特征进行立体匹配的关键因素。我们进一步研究了预训练特征的实例级信息的作用，证明它有利于立体匹配，同时可以在基于卷积的特征融合过程中被抑制。基于注意力机制，所提出的 DN 模块有效地利用了预训练特征中的实例级信息。此外，我们提供了对效率与准确性权衡的理解，得出的结论是，考虑到效率，使用预先训练的特征也可以是一个很好的替代方案。