CNN-SLAM：实时稠密单目SLAM，采用深度学习预测算法 ，CNN-SLAM: Real-time dense monocular SLAM with learned depth prediction。
摘要：
鉴于卷积神经网络（CNN）深度预测的最新进展，本文研究了深度神经网络的预测深度图，可以部署用于精确和密集的单目重建。我们提出了一种方法，其中CNN预测的稠密深度图与通过直接单目SLAM获得的深度测量自然地融合在一起。我们的融合方案在图像定位中优于单目SLAM方法，例如沿低纹理区域，反之亦然。我们展示了使用深度预测来估计重建的绝对尺度，从而克服了单眼SLAM的主要局限性之一。最后，我们提出一个框架，从单个帧获得的语义标签有效地融合了密集的SLAM，从单个视图产生语义相干的场景重构。两个基准数据集的评估结果显示了我们的方法的鲁棒性和准确性
摘要：
Given the recent advances in depth prediction from Convolutional Neural Networks (CNNs), this paper investigates how predicted depth maps from a deep neural network can be deployed for accurate and dense monocular reconstruction. We propose a method where CNN-predicted dense depth maps are naturally fused together with depth measurements obtained from direct monocular SLAM. Our fusion scheme privileges depth prediction in image locations where monocular SLAM approaches tend to fail, e.g. along low-textured regions, and vice-versa. We demonstrate the use of depth prediction for estimating the absolute scale of the reconstruction, hence overcoming one of the major limitations of monocular SLAM. Finally, we propose a framework to efficiently fuse semantic labels, obtained from a single frame, with dense SLAM, yielding semantically coherent scene reconstruction from a single view. Evaluation results on two benchmark datasets show the robustness and accuracy of our approach.
链接：
http://campar.in.tum.de/Chair/ProjectCNNSLAM
原文链接：
https://m.weibo.cn/5501429448/4131227164344283
