arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2110.02582cs.CVcs.LG
收藏

FADNet++:使用可配置网络进行实时的和精确的视差估计

FADNet++: Real-Time and Accurate Disparity Estimation with Configurable Networks

Hong Kong Baptist University(香港浸会大学);The Hong Kong University of Science and Technology(香港科技大学)

Qiang Wang, Shaohuai Shi, Shizhen Zheng, Kaiyong Zhao, Xiaowen Chu

摘要:

深度神经网络(DNN)在计算机视觉领域取得了巨大成功。视差估计问题倾向于由DNN解决,DNN比传统的手工制作的基于特征的方法实现更好的预测精度。然而,现有的DNN很难同时提供高效的计算和丰富的表达能力,这使得它们难以部署在实时的【形】高质量的应用中,特别是在移动设备上。为此,我们提出了一个高效、准确、可配置的深度网络,用于视差估计,名为FADNet++。FADNet++利用几种自由的网络设计和训练技术,可以通过快速的模型推理速度提高其准确性,适用于实时的【形】应用。此外,它使用户能够轻松配置不同大小的模型,以平衡准确性和推理效率。我们进行了广泛的实验,以证明FADNet++在从服务器到移动平台的六个GPU设备中的合成和真实数据集上的有效性。实验结果表明,FADNet++及其变体实现了最先进的预测精度,并且运行速度比现有的3D模型快了一个数量级。在移动GPU上以每秒15帧(FPS)以上的速度运行的限制下,FADNet++为SceneFlow数据集实现了新的最先进的结果。

英文摘要:

Deep neural networks (DNNs) have achieved great success in the area of computer vision. The disparity estimation problem tends to be addressed by DNNs which achieve much better prediction accuracy than traditional hand-crafted feature-based methods. However, the existing DNNs hardly serve both efficient computation and rich expression capability, which makes them difficult for deployment in real-time and high-quality applications, especially on mobile devices. To this end, we propose an efficient, accurate, and configurable deep network for disparity estimation named FADNet++. Leveraging several liberal network design and training techniques, FADNet++ can boost its accuracy with a fast model inference speed for real-time applications. Besides, it enables users to easily configure different sizes of models for balancing accuracy and inference efficiency. We conduct extensive experiments to demonstrate the effectiveness of FADNet++ on both synthetic and realistic datasets among six GPU devices varying from server to mobile platforms. Experimental results show that FADNet++ and its variants achieve state-of-the-art prediction accuracy, and run at a significant order of magnitude faster speed than existing 3D models. With the constraint of running at above 15 frames per second (FPS) on a mobile GPU, FADNet++ achieves a new state-of-the-art result for the SceneFlow dataset.

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。

↑