Efficient unsupervised monocular depth estimation using attention guided generative adversarial network
Efficient unsupervised monocular depth estimation using attention guided generative adversarial network
复制标题
DOI：
10.1007/s11554-021-01092-0
复制
发表时间：
2021-03
影响因子：
3
通讯作者：
Sumanta Bhattacharyya;Ju Shen;Stephen Welch;Chen Chen-Chen
中科院分区：
文献类型：
--
作者：
Sumanta Bhattacharyya;Ju Shen;Stephen Welch;Chen Chen-Chen
基于深度学习的深度估计方法正在迅速发展，在许多领域提供比传统计算机视觉方法更好的性能。然而，对于许多关键应用来说，基于深度学习的尖端方法需要太多的计算开销才能在操作上可行。对于利用对抗性学习的深度估计方法尤其如此，例如生成对抗网络（GAN）。在本文中，我们提出了一种计算高效的 GAN，使用分解卷积和注意力机制进行无监督单目深度估计。具体来说，我们在网络内部利用 ESPNetv2 的深度扩展可分离卷积（EESP）模块的极其高效空间金字塔，与之前的无监督 GAN 方法相比，分别减少了模型参数数量、FLOP 和推理时间。最后，我们提出了一种上下文感知的注意力架构来生成面向细节的深度图像。我们在两个基准数据集 KITTI 和 Cityscapes 上展示了我们提出的模型的卓越性能。我们还在本文末尾提供了更多定性示例（图 8）。
Deep-learning-based approaches to depth estimation are rapidly advancing, offering better performance over traditional computer vision approaches across many domains. However, for many critical applications, cutting-edge deep-learning based approaches require too much computational overhead to be operationally feasible. This is especially true for depth-estimation methods that leverage adversarial learning, such as Generative Adversarial Networks (GANs). In this paper, we propose a computationally efficient GAN for unsupervised monocular depth estimation using factorized convolutions and an attention mechanism. Specifically, we leverage the Extremely Efficient Spatial Pyramid of Depth-wise Dilated Separable Convolutions (EESP) module of ESPNetv2 inside the network, leading to a total reduction of,, andin the number of model parameters, FLOPs, and inference time respectively, as compared to the previous unsupervised GAN approach. Finally, we propose a context-aware attention architecture to generate detail-oriented depth images. We demonstrate superior performance of our proposed model on two benchmark datasets KITTI and Cityscapes. We have also provided more qualitative examples (Fig. 8) at the end of this paper.