Abstract
Although multi-scale concepts have recently proven useful for recurrent network architectures in the field of optical flow and stereo, they have not been considered for image-based scene flow so far. Hence, based on a single-scale recurrent scene flow backbone, we develop a multi-scale approach that generalizes successful hierarchical ideas from optical flow to image-based scene flow. By considering suitable concepts for the feature and the context encoder, the overall coarse-to-fine framework and the training loss, we succeed to design a scene flow approach that outperforms the current state of the art on KITTI and Spring by 8.7%(3.89 vs. 4.26) and 65.8% (9.13 vs. 26.71), respectively. Our code is available at this https URL.
Abstract (translated)
尽管多尺度概念最近在光流和立体视觉领域被证明对递归网络架构非常有用，但迄今为止它们尚未应用于基于图像的场景流量。因此，我们以单尺度递归场景流量主干为基础，开发了一种多尺度方法，将光学领域的成功分层理念推广到基于图像的场景流量中。通过考虑特征编码器和上下文编码器中的合适概念、整体从粗到精框架以及训练损失，我们设计出一种在KITTI数据集上优于当前最先进技术8.7%（3.89 vs. 4.26）并在Spring数据集中表现更好，提高了65.8%（9.13 vs. 26.71）的场景流量方法。我们的代码可在[此链接](https://example.com)获取。
URL
https://arxiv.org/abs/2506.01443
