论文标题
端到端的立体声算法是否不足以填充信息？
Do End-to-end Stereo Algorithms Under-utilize Information?
论文作者
论文摘要
立体声匹配的深网通常利用2D或3D卷积编码器架构来汇总成本，并将成本量正规化，以进行准确的差异估计。由于内容不敏感的卷积，下采样和上采样操作，这些成本汇总机制无法充分利用图像中可用的信息。差异图遇到了过度平滑的遮挡边界，并且在薄结构中的错误预测。在本文中，我们展示了如何将深层自适应过滤和可区分的半全球聚合集成到现有的2D和3D卷积网络中，以进行端到端立体声匹配，从而提高了精度。这些改进是由于利用来自图像的RGB信息作为信号来动态指导匹配过程，此外是我们试图通过图像匹配的信号。我们在Kitti 2015和Virtual Kitti 2数据集上显示了广泛的实验结果，以比较四个集成了四个自适应过滤器（分段 - 意识到双边滤波，动态过滤网络，Pixel Affaptive Adiptive Rosecrolution and Emai-Glob gromecation inst Irchitecration intructal contectection contection and incettection contectiation and artate contectection contection and incettal contectiation contection and inactection contection and Houstection conteration和GANET）。我们的代码可在https://github.com/ccj5351/dafstereonets上找到。
Deep networks for stereo matching typically leverage 2D or 3D convolutional encoder-decoder architectures to aggregate cost and regularize the cost volume for accurate disparity estimation. Due to content-insensitive convolutions and down-sampling and up-sampling operations, these cost aggregation mechanisms do not take full advantage of the information available in the images. Disparity maps suffer from over-smoothing near occlusion boundaries, and erroneous predictions in thin structures. In this paper, we show how deep adaptive filtering and differentiable semi-global aggregation can be integrated in existing 2D and 3D convolutional networks for end-to-end stereo matching, leading to improved accuracy. The improvements are due to utilizing RGB information from the images as a signal to dynamically guide the matching process, in addition to being the signal we attempt to match across the images. We show extensive experimental results on the KITTI 2015 and Virtual KITTI 2 datasets comparing four stereo networks (DispNetC, GCNet, PSMNet and GANet) after integrating four adaptive filters (segmentation-aware bilateral filtering, dynamic filtering networks, pixel adaptive convolution and semi-global aggregation) into their architectures. Our code is available at https://github.com/ccj5351/DAFStereoNets.
