缩放和学习：将深度立体匹配推广到新领域
Zoom and Learn: Generalizing Deep Stereo Matching to Novel Domains
摘要：
尽管最近使用卷积神经网络（CNN）的立体匹配取得了成功，但将预训练的深度立体模型推广到新领域仍然很困难。一个主要的困难是收集准确的地面实况差异的立体声对在目标域。在这项工作中，我们提出了一种自适应方法的CNN训练，利用合成训练数据（地面实况差异）和立体声对在新的域（没有地面实况）。我们的方法是由两个经验观察。通过将不同域的真实立体对馈送到用合成数据预训练的立体模型，我们看到：i）预训练的模型不能很好地推广到新的域，在边界和不适定区域产生伪影;然而，ii）馈送上采样的立体对导致具有额外细节的视差图。为了避免i），同时利用ii），我们用图拉普拉斯正则化来表示迭代优化问题。在每次迭代中，CNN都能更好地适应新的域：我们让CNN学习自己的更高分辨率输出;同时，实施图拉普拉斯正则化，以区别性地保留所需的边缘，同时平滑伪影。我们证明了我们的方法在两个领域的有效性：智能手机摄像头收集的日常场景，并在驾驶汽车捕捉的街景。
英文摘要：
Despite the recent success of stereo matching with convolutional neural networks (CNNs), it remains arduous to generalize a pre-trained deep stereo model to a novel domain. A major difficulty is to collect accurate ground-truth disparities for stereo pairs in the target domain. In this work, we propose a self-adaptation approach for CNN training, utilizing both synthetic training data (with ground-truth disparities) and stereo pairs in the new domain (without ground-truths). Our method is driven by two empirical observations. By feeding real stereo pairs of different domains to stereo models pre-trained with synthetic data, we see that: i) a pre-trained model does not generalize well to the new domain, producing artifacts at boundaries and ill-posed regions; however, ii) feeding an up-sampled stereo pair leads to a disparity map with extra details. To avoid i) while exploiting ii), we formulate an iterative optimization problem with graph Laplacian regularization. At each iteration, the CNN adapts itself better to the new domain: we let the CNN learn its own higher-resolution output; at the meanwhile, a graph Laplacian regularization is imposed to discriminatively keep the desired edges while smoothing out the artifacts. We demonstrate the effectiveness of our method in two domains: daily scenes collected by smartphone cameras, and street views captured in a driving car.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
