arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2106.03043cs.CV
收藏

基于遮挡感知的四维光场深度无监督学习

Occlusion-aware Unsupervised Learning of Depth from 4-D Light Fields

City University of Hong Kong(香港城市大学)

Jing Jin, Junhui Hou

摘要:

深度估计是四维光场处理和分析中的一个基本问题。尽管最近的基于监督学习的光场深度估计方法已经显著地提高了传统的基于优化的方法的准确性和效率,但是这些方法依赖于具有地面实况深度图的光场数据的训练,这对于获得真实世界的光场数据是具有挑战性的或者甚至是不可用的。此外,由于真实世界和合成数据之间不可避免的差距(或域差异),当将用合成数据训练的模型推广到真实世界数据时,它们可能会遭受严重的性能下降。相比之下,我们提出了一种基于无监督学习的方法,该方法在训练期间不需要地面实况深度作为监督。具体而言,基于光场数据的独特几何结构的基本知识,我们提出了一种遮挡感知策略,以提高对遮挡区域的准确性,其中我们探索光场视图的子集之间的角度相干性来估计初始深度图,并利用受约束的无监督损失来学习其相应的可靠性,以最终进行深度预测。此外,我们采用了一个多尺度网络与加权平滑损失来处理无纹理区域。在合成数据上的实验结果表明,该方法能够显著缩小无监督方法和有监督方法之间的性能差距,并在计算量明显降低的情况下,生成与传统方法相当的深度图。此外,在真实数据集上的实验表明,我们的方法可以避免在监督方法中出现的域移位问题,展示了我们的方法的巨大潜力。

英文摘要:

Depth estimation is a fundamental issue in 4-D light field processing and analysis. Although recent supervised learning-based light field depth estimation methods have significantly improved the accuracy and efficiency of traditional optimization-based ones, these methods rely on the training over light field data with ground-truth depth maps which are challenging to obtain or even unavailable for real-world light field data. Besides, due to the inevitable gap (or domain difference) between real-world and synthetic data, they may suffer from serious performance degradation when generalizing the models trained with synthetic data to real-world data. By contrast, we propose an unsupervised learning-based method, which does not require ground-truth depth as supervision during training. Specifically, based on the basic knowledge of the unique geometry structure of light field data, we present an occlusion-aware strategy to improve the accuracy on occlusion areas, in which we explore the angular coherence among subsets of the light field views to estimate initial depth maps, and utilize a constrained unsupervised loss to learn their corresponding reliability for final depth prediction. Additionally, we adopt a multi-scale network with a weighted smoothness loss to handle the textureless areas. Experimental results on synthetic data show that our method can significantly shrink the performance gap between the previous unsupervised method and supervised ones, and produce depth maps with comparable accuracy to traditional methods with obviously reduced computational cost. Moreover, experiments on real-world datasets show that our method can avoid the domain shift problem presented in supervised methods, demonstrating the great potential of our method.

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。

↑