How important are training details and datasets to recent optical flow models
like RAFT? And do they generalize? To explore these questions, rather than
develop a new model, we revisit three prominent models, PWC-Net, IRR-PWC and
RAFT, with a common set of modern training techniques and datasets, and observe
significant performance gains, demonstrating the importance and generality of
these training details. Our newly trained PWC-Net and IRR-PWC models show
surprisingly large improvements, up to 30% versus original published results on
Sintel and KITTI 2015 benchmarks. They outperform the more recent Flow1D on
KITTI 2015 while being 3x faster during inference. Our newly trained RAFT
achieves an Fl-all score of 4.31% on KITTI 2015, more accurate than all
published optical flow methods at the time of writing. Our results demonstrate
the benefits of separating the contributions of models, training techniques and
datasets when analyzing performance gains of optical flow methods. Our source
code will be publicly available.

通过使用相同的现代培训技术和数据集，作者重访了三种主要的光流模型 PWC-Net，IRR-PWC 和 RAFT，观察到显着的性能提升，并表明这些培训细节的重要性和普遍性。新培训的 PWC-Net 和 IRR-PWC 模型显示出惊人的大幅改进，在 Sintel 和 KITTI 2015 基准测试中，其对比原始发布结果提高了 30％，在推理期间的运行速度也更快。RAF 的新培训实现了在 KITTI 2015 上的 Fl-all 得分 4.31％，比当时所有已发布的光流方法都更准确。

光流分离架构与训练

Disentangling Architecture and Training for Optical Flow

Learning long-term spatial-temporal features are critical for many video
analysis tasks. However, existing video segmentation methods predominantly rely
on static image segmentation techniques, and methods capturing temporal
dependency for segmentation have to depend on pretrained optical flow models,
leading to suboptimal solutions for the problem. End-to-end sequential learning
to explore spatialtemporal features for video segmentation is largely limited
by the scale of available video segmentation datasets, i.e., even the largest
video segmentation dataset only contains 90 short video clips. To solve this
problem, we build a new large-scale video object segmentation dataset called
YouTube Video Object Segmentation dataset (YouTube-VOS). Our dataset contains
4,453 YouTube video clips and 94 object categories. This is by far the largest
video object segmentation dataset to our knowledge and has been released at
this http URL We further evaluate several existing state-of-the-art
video object segmentation algorithms on this dataset which aims to establish
baselines for the development of new algorithms in the future.

此篇论文介绍了一个新的大型视频对象分割数据集（YouTube-VOS），目前是已知最大的数据集之一，其中包含 4,453 个 YouTube 视频剪辑和 94 个物体类别，并在此数据集上评估了几种现有的最先进的视频对象分割算法，以建立未来新算法的基础。