Depthformer：局部全局信息融合的单目深度估计多尺度视觉Transformer
Depthformer : Multiscale Vision Transformer For Monocular Depth Estimation With Local Global Information Fusion
摘要：
基于注意力的模型（如Transformers）在密集预测任务（如语义分割）上表现出出色的性能，这是因为它们能够捕获图像中的长距离依赖性。然而，Transformers的单目深度预测的好处很少被探索到目前为止。本文基准各种基于变换的模型的深度估计任务的室内NYUV2数据集和室外KITTI数据集。我们提出了一种新的基于注意力的架构，用于单目深度估计的Depthformer，其使用多头自注意力来产生多尺度特征图，这些特征图通过我们提出的解码器网络有效地组合。我们还提出了一个Transbins模块，它将深度范围划分为bin，每个图像的中心值是自适应估计的。估计的最终深度是每个像素的面元中心的线性组合。Transbins模块在编码阶段使用Transformer模块来利用全局感受野。在NYUV2和KITTI深度估计基准上的实验结果表明，我们提出的方法在均方根误差（RMSE）方面分别提高了3.3%和3.3%。代码可在https://github.com/ashutosh1807/Depthformer.git上获得。
英文摘要：
Attention-based models such as transformers have shown outstanding performance on dense prediction tasks, such as semantic segmentation, owing to their capability of capturing long-range dependency in an image. However, the benefit of transformers for monocular depth prediction has seldom been explored so far. This paper benchmarks various transformer-based models for the depth estimation task on an indoor NYUV2 dataset and an outdoor KITTI dataset. We propose a novel attention-based architecture, Depthformer for monocular depth estimation that uses multi-head self-attention to produce the multiscale feature maps, which are effectively combined by our proposed decoder network. We also propose a Transbins module that divides the depth range into bins whose center value is estimated adaptively per image. The final depth estimated is a linear combination of bin centers for each pixel. Transbins module takes advantage of the global receptive field using the transformer module in the encoding stage. Experimental results on NYUV2 and KITTI depth estimation benchmark demonstrate that our proposed method improves the state-of-the-art by 3.3%, and 3.3% respectively in terms of Root Mean Squared Error (RMSE). Code is available at https://github.com/ashutosh1807/Depthformer.git.
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。
