arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.07628cs.CV
收藏

基于区域分离的全天图像自监督单目深度估计

Self-supervised Monocular Depth Estimation for All Day Images using Domain Separation

Institute of Cyber-Systems and Control, Zhejiang University(浙江大学控制科学与工程学院);Baidu Research(百度研究院);National Engineering Laboratory of Deep Learning Technology and Application(深度学习技术及应用国家工程实验室)

Lina Liu, Xibin Song, Mengmeng Wang, Yong Liu, Liangjun Zhang

摘要:

基于DCNN的自监督深度估计方法取得了显著的效果。然而,这些方法中的大多数只能处理白天或夜间的图像,而它们的性能下降全天图像由于大的域偏移和白天和夜间图像之间的光照变化。为了缓解这些限制,我们提出了一个域分离的网络,全天图像的自我监督深度估计。具体地,为了减轻干扰项(照明等)的负面影响,我们将昼夜图像对的信息划分为两个互补的子空间:私有域和不变域,其中前者包含唯一信息(光照等)。白天和夜晚的图像,后者包含基本的共享信息(纹理等)。同时,为了保证白天和夜晚图像包含相同的信息,区域分离网络将白天图像和相应的夜晚图像(由GAN生成)作为输入,通过正交性和相似性损失来学习私有和不变特征提取器,可以缓解区域间隙,从而可以期望更好的深度图。同时,重建和光度损失被用于有效地估计互补信息和深度图。实验结果表明,我们的方法实现了国家的最先进的深度估计的结果,全天图像上具有挑战性的牛津RobotCar数据集,证明了我们提出的方法的优越性。

英文摘要:

Remarkable results have been achieved by DCNN based self-supervised depth estimation approaches. However, most of these approaches can only handle either day-time or night-time images, while their performance degrades for all-day images due to large domain shift and the variation of illumination between day and night images. To relieve these limitations, we propose a domain-separated network for self-supervised depth estimation of all-day images. Specifically, to relieve the negative influence of disturbing terms (illumination, etc.), we partition the information of day and night image pairs into two complementary sub-spaces: private and invariant domains, where the former contains the unique information (illumination, etc.) of day and night images and the latter contains essential shared information (texture, etc.). Meanwhile, to guarantee that the day and night images contain the same information, the domain-separated network takes the day-time images and corresponding night-time images (generated by GAN) as input, and the private and invariant feature extractors are learned by orthogonality and similarity loss, where the domain gap can be alleviated, thus better depth maps can be expected. Meanwhile, the reconstruction and photometric losses are utilized to estimate complementary information and depth maps effectively. Experimental results demonstrate that our approach achieves state-of-the-art depth estimation results for all-day images on the challenging Oxford RobotCar dataset, proving the superiority of our proposed approach.

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。

↑