Depth estimation from stereo images is essential to many applications such as robotics and autonomous vehicles, most of which ask for the real-time response, high energy and storage efficiency. Recent work has shown deep neural networks (DNN) perform extremely well for stereo estimation. However, these state-of-the-art DNN based algorithms are challenging to be deployed into real-world applications due to the high computational complexities of DNNs. Most of them are too slow for real-time inference and require several seconds of GPU computation to process image frames. In this article, we address the problem of fast stereo estimation and propose an efficient and light-weighted stereo matching system, called StereoBit, to produce a disparity map in a real-time manner while achieving close to state-of-the-art accuracy. To achieve this goal, we propose a binary neural network to generate weighted Hamming distance for an efficient similarity join in stereo estimation. In addition, we propose a novel approximation approach to derive StereoBit network directly from the well-trained network with the cosine similarity. Our approximation strategies enable a significant speedup while maintaining almost the same accuracy compared to the network with the cosine similarity. Furthermore, we present an optimization framework for fully exploiting the computing power of StereoBit. The framework provides a significant speedup of stereo estimation routines, and at the same time, reduces the memory usage for storing parameters. The effectiveness of StereoBit is evaluated by comprehensive experiments. StereoBit can achieve 60 frames per second on an NVIDIA TITAN Xp GPU on KITTI 2012 benchmark while achieving 3-pixel non-occluded stereo error 3.56 percent.

中文翻译：

---

使用二进制神经网络的 GPU 加速实时立体估计

立体图像的深度估计对于机器人和自动驾驶汽车等许多应用至关重要，其中大多数应用要求实时响应、高能量和存储效率。最近的工作表明，深度神经网络 (DNN) 在立体估计方面表现非常出色。然而，由于 DNN 的高计算复杂性，这些最先进的基于 DNN 的算法很难部署到实际应用中。它们中的大多数对于实时推理来说太慢了，并且需要几秒钟的 GPU 计算来处理图像帧。在本文中，我们解决了快速立体估计的问题，并提出了一种高效且轻量级的立体匹配系统，称为 StereoBit，以实时方式生成视差图，同时实现接近最先进的精度. 为了实现这一目标，我们提出了一个二元神经网络来生成加权汉明距离，以便在立体估计中进行有效的相似性连接。此外，我们提出了一种新的近似方法，可以直接从具有余弦相似度的训练有素的网络中导出 StereoBit 网络。与具有余弦相似度的网络相比，我们的近似策略在保持几乎相同的精度的同时实现了显着的加速。此外，我们提出了一个优化框架，以充分利用 StereoBit 的计算能力。该框架显着加快了立体估计例程，同时减少了用于存储参数的内存使用量。StereoBit 的有效性通过综合实验进行评估。