HITNet：用于实时的立体匹配的分层迭代瓦片细化网络
HITNet: Hierarchical Iterative Tile Refinement Network for Real-time Stereo Matching
摘要：
本文介绍了HITNet，一种新的神经网络结构的实时的【形】立体匹配。与许多最近的神经网络方法相反，这些方法在全成本体积上操作并依赖于3D卷积，我们的方法不显式地构建体积，而是依赖于快速多分辨率初始化步骤，可微分的2D几何传播和扭曲机制来推断视差假设。为了实现高水平的准确性，我们的网络不仅在几何上对视差进行推理，而且还推断出倾斜平面假设，从而可以更准确地执行几何扭曲和上采样操作。我们的架构本身就是多分辨率的，允许跨不同级别的信息传播。多个实验证明了所提出的方法的有效性，在一小部分的国家的最先进的方法所需的计算。在撰写本文时，HITNet在ETH 3D网站上发布的所有双视图立体声指标中排名第1 - 3位，在Middlebury-v3上的所有端到端学习方法中的大多数指标中排名第1，在流行的KITTI 2012和2015基准测试中排名第1，其中发布的方法快于100毫秒。
英文摘要：
This paper presents HITNet, a novel neural network architecture for real-time stereo matching. Contrary to many recent neural network approaches that operate on a full cost volume and rely on 3D convolutions, our approach does not explicitly build a volume and instead relies on a fast multi-resolution initialization step, differentiable 2D geometric propagation and warping mechanisms to infer disparity hypotheses. To achieve a high level of accuracy, our network not only geometrically reasons about disparities but also infers slanted plane hypotheses allowing to more accurately perform geometric warping and upsampling operations. Our architecture is inherently multi-resolution allowing the propagation of information across different levels. Multiple experiments prove the effectiveness of the proposed approach at a fraction of the computation required by state-of-the-art methods. At the time of writing, HITNet ranks 1st-3rd on all the metrics published on the ETH3D website for two view stereo, ranks 1st on most of the metrics among all the end-to-end learning approaches on Middlebury-v3, ranks 1st on the popular KITTI 2012 and 2015 benchmarks among the published methods faster than 100ms.
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。
