In this work, we propose a new approach for dense disparity estimation in a global energy minimization framework. We propose to use a feature matching cost which is defined using the learned hierarchical features of given left and right stereo images and we combine it with the pixel-based intensity matching cost in our energy function. Hierarchical features are learned using the deep deconvolutional network which is trained in an unsupervised way using a database consisting of large number of stereo images. In order to perform the regularization, we propose to use the inhomogeneous Gaussian Markov random field (IGMRF) and sparsity priors in our energy function. A sparse autoencoder -based approach is proposed for learning and inferring the sparse representation of disparities. The IGMRF prior captures the smoothness as well as preserves sharp discontinuities while the sparsity prior captures the sparseness in the disparity map. Finally, an iterative two-phase algorithm is proposed to estimate the dense disparity map where in phase one, sparse representation of disparities are inferred from the trained sparse autoencoder, and IGMRF parameters are computed, keeping the disparity map fixed and in phase two, the disparity map is refined by minimizing the energy function using graph cuts, with other parameters fixed. Experimental results on the Middlebury stereo benchmarks demonstrate the effectiveness of the proposed approach.

中文翻译：

---

基于无监督特征学习的用于稀疏视差估计的学习稀疏和基于IGMRF的正则化框架

在这项工作中，我们提出了一种在全球能源最小化框架中进行密集视差估算的新方法。我们建议使用特征匹配成本，该特征匹配成本是根据给定的左右立体图像的学习层次特征定义的，并将其与能量函数中基于像素的强度匹配成本相结合。使用 深度反卷积网络学习层次特征，该 深度反卷积网络 使用包含大量立体图像的数据库以无监督的方式进行训练。为了执行正则化，我们建议在能量函数中使用非均匀高斯马尔可夫随机场（IGMRF）和稀疏先验。一个 稀疏自动编码器 提出了一种基于学习的方法来学习和推断稀疏的视差表示。IGMRF先验可捕获平滑度并保留尖锐的不连续性，而稀疏先验可捕获视差图中的稀疏性。最后，提出了一种迭代两阶段算法来估计密集视差图，其中在第一阶段中，从经过训练的稀疏自动编码器推断出视差的稀疏表示，并计算IGMRF参数，使视差图保持固定，在第二阶段，视差图通过使用图割最小化能量函数（其他参数固定）来优化。在Middlebury立体声基准上的实验结果证明了该方法的有效性。