DCVNet：用于快速光流的膨胀代价体网络
DCVNet: Dilated Cost Volume Networks for Fast Optical Flow
AI总结：
本文提出DCVNet，通过构建不同膨胀因子的代价体同时捕捉大小位移，利用U-Net转换插值权重，实现单次前馈处理，达到与现有方法相当的精度并支持实时推理。
摘要：
代价体捕捉两幅输入图像间可能对应关系的相似性，是先进光流方法中的关键组成部分。在采样对应关系以构建代价体时，需要较大的邻域半径来处理大位移，这带来了显著的计算负担。为了解决这一问题，通常采用从粗到细或循环处理代价体的方式，此时在具有小半径的局部邻域内进行对应关系采样即可满足需求。在本文中，我们提出了一种替代方案，通过构建具有不同膨胀因子的代价体来同时捕捉小位移和大位移。我们采用带有跳跃连接的U-Net将膨胀代价体转换为所有可能捕捉到的位移之间的插值权重，从而得到光流。我们提出的模型DCVNet仅需以简单的前馈方式处理一次代价体，不依赖顺序处理策略。DCVNet在精度上与现有方法相当，并实现了实时推理（在中端1080ti GPU上达到30帧/秒）。代码和模型权重可在https://github.com/neu-vi/ezflow获取。
英文摘要：
The cost volume, capturing the similarity of possible correspondences across two input images, is a key ingredient in state-of-the-art optical flow approaches. When sampling correspondences to build the cost volume, a large neighborhood radius is required to deal with large displacements, introducing a significant computational burden. To address this, coarse-to-fine or recurrent processing of the cost volume is usually adopted, where correspondence sampling in a local neighborhood with a small radius suffices. In this paper, we propose an alternative by constructing cost volumes with different dilation factors to capture small and large displacements simultaneously. A U-Net with skip connections is employed to convert the dilated cost volumes into interpolation weights between all possible captured displacements to get the optical flow. Our proposed model DCVNet only needs to process the cost volume once in a simple feedforward manner and does not rely on the sequential processing strategy. DCVNet obtains comparable accuracy to existing approaches and achieves real-time inference (30 fps on a mid-end 1080ti GPU). The code and model weights are available at https://github.com/neu-vi/ezflow.
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。
