ScaleNet: A Shallow Architecture for Scale Estimation
ScaleNet: A Shallow Architecture for Scale Estimation
复制标题
DOI：
10.1109/cvpr52688.2022.01247
复制
发表时间：
2021-12
期刊：
影响因子：
--
通讯作者：
Axel Barroso Laguna;Yurun Tian;K. Mikolajczyk
中科院分区：
文献类型：
--
作者：
Axel Barroso Laguna;Yurun Tian;K. Mikolajczyk
本文主要研究图像间尺度因子的估计问题。我们将尺度估计问题表述为对尺度因子的概率分布的预测。我们设计了一个新的架构，SealeNet，它利用扩展卷积以及自相关层和相互相关层来预测图像之间的尺度。我们证明了用估计尺度校正图像可以显著改善各种任务和方法的性能。具体来说，我们展示了ScaleNet如何与稀疏局部特征和密集对应网络相结合，以改善不同基准和数据集的相机姿态估计，3D重建或密集几何匹配。我们对几个任务进行了广泛的评估，并分析了SealeNet的计算开销。代码、评估协议和训练过的模型可在https://github.com/axelBarroso/ScaleNet上公开获得。
In this paper, we address the problem of estimating scale factors between images. We formulate the scale estimation problem as a prediction of a probability distribution over scale factors. We design a new architecture, SealeNet, that exploits dilated convolutions as well as self- and cross-correlation layers to predict the scale between images. We demonstrate that rectifying images with estimated scales leads to significant performance improvements for various tasks and methods. Specifically, we show how ScaleNet can be combined with sparse local features and dense correspondence networks to improve camera pose estimation, 3D reconstruction, or dense geometric matching in different benchmarks and datasets. We provide an extensive evaluation on several tasks, and analyze the computational overhead of SealeNet. The code, evaluation protocols, and trained models are publicly available at https://github.com/axelBarroso/ScaleNet.