arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1906.00050cs.CV
收藏

DISCO:使用上下文从立体声进行深度推断

DISCO: Depth Inference from Stereo using Context

Indian Institute of Technology Madras(印度理工学院马德拉斯分校);BITS Pilani(比尔拉科学技术学院皮拉尼分校)

Kunal Swami, Kaushik Raghavan, Nikhilanj Pelluri, Rituparna Sarkar, Pankaj Bajpai

摘要:

最近的基于深度学习的方法已经优于经典的立体匹配方法。然而,当前基于深度学习的端到端立体匹配方法采用具有跳过连接的通用编码器-解码器风格的网络。为了限制计算需求,许多网络执行过度的下采样,这导致有用的低级信息的显著丢失。此外,许多网络设计没有利用丰富的多尺度上下文信息。在这项工作中,我们通过仔细设计网络架构来解决上述问题,以在整个网络中保留所需的空间信息,同时实现大的有效感受野来提取多尺度上下文信息。我们首次创建了一个反映使用智能手机捕获的真实图像的合成视差数据集;这使我们能够在常见的真实图像上获得最先进的结果。所提出的模型DISCO在合成场景流数据集上进行了预训练,并在流行的基准测试和我们内部具有挑战性的现实生活图像数据集上进行了评估。该模型在质量和定量指标方面优于现有的最先进的方法。

英文摘要:

Recent deep learning based approaches have outperformed classical stereo matching methods. However, current deep learning based end-to-end stereo matching methods adopt a generic encoder-decoder style network with skip connections. To limit computational requirement, many networks perform excessive down sampling, which results in significant loss of useful low-level information. Additionally, many network designs do not exploit the rich multi-scale contextual information. In this work, we address these aforementioned problems by carefully designing the network architecture to preserve required spatial information throughout the network, while at the same time achieve large effective receptive field to extract multiscale contextual information. For the first time, we create a synthetic disparity dataset reflecting real life images captured using a smartphone; this enables us to obtain state-of-the-art results on common real life images. The proposed model DISCO is pre-trained on the synthetic Scene Flow dataset and evaluated on popular benchmarks and our in-house dataset of challenging real life images. The proposed model outperforms existing state-of-the-art methods in terms of quality as well as quantitative metrics.

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。

↑