用深度模型和运动基底，让光流计算更轻量高效
FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases
- 结合单图深度模型与低维运动参数化，设计轻量架构
- 仅需消费级显卡训练，性能超越SEA-RAFT 10%~15%
- 适合资源受限场景下的高精度光流应用
我们提出FlowSeek，一种新型光流框架，训练所需硬件资源极低。该方法融合了最新光流网络设计、单图深度基础模型以及经典的低维运动参数化，构建了一个紧凑而精准的结构。FlowSeek仅在单张消费级GPU上训练，硬件预算约为近期多数方法的1/8，但在Sintel Final和KITTI数据集上仍实现卓越的跨数据集泛化能力，相对前序最优方法SEA-RAFT分别提升10%和15%，并在Spring与LayeredFlow数据集上表现优异。
原文摘要 · Abstract (English)
We present FlowSeek, a novel framework for optical flow requiring minimal hardware resources for training. FlowSeek marries the latest advances on the design space of optical flow networks with cutting-edge single-image depth foundation models and classical low-dimensional motion parametrization, implementing a compact, yet accurate architecture. FlowSeek is trained on a single consumer-grade GPU, a hardware budget about 8x lower compared to most recent methods, and still achieves superior cross-dataset generalization on Sintel Final and KITTI, with a relative improvement of 10 and 15% over the previous state-of-the-art SEA-RAFT, as well as on Spring and LayeredFlow datasets.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。