arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2407.10802cs.CVcs.LGcs.RO
收藏

基于运动先验的对比度最大化用于密集连续时间运动估计

Motion-prior Contrast Maximization for Dense Continuous-Time Motion Estimation

TU Berlin(柏林工业大学);SCIoI Excellence Cluster(SCIoI卓越集群);University of Pennsylvania(宾夕法尼亚大学);Einstein Center Digital Future(爱因斯坦数字未来中心);Robotics Institute Germany(德国机器人研究所);Archimedes(阿基米德机构);Athena RC(雅典娜研究中心)

Friedhelm Hamann, Ziyun Wang, Ioannis Asmanis, Kenneth Chaney, Guillermo Gallego, Kostas Daniilidis

AI总结:

本文提出一种结合对比度最大化与非线性运动先验的自监督损失,用于事件相机密集连续时间运动估计,在EVIMO2和DSEC基准上显著提升性能。

摘要:

当前的光流和点跟踪方法严重依赖合成数据集。事件相机是一种新型视觉传感器,在具有挑战性的视觉条件下具有优势,但由于当前事件模拟器的局限性,最先进的基于帧的方法难以直接适应事件数据。我们提出了一种新颖的自监督损失,将对比度最大化框架与像素级轨迹形式的非线性运动先验相结合,并提出了一种高效解决方案来解决非线性轨迹与事件之间的高维分配问题。其有效性在两个场景中得到验证:在密集连续时间运动估计中,我们的方法将合成训练模型在真实世界数据集EVIMO2上的零样本性能提高了29%;在光流估计中,我们的方法将简单的UNet提升到DSEC光流基准上自监督方法中的最先进性能。我们的代码可在 https://github.com/tub-rip/MotionPriorCMax 获取。

英文摘要:

Current optical flow and point-tracking methods rely heavily on synthetic datasets. Event cameras are novel vision sensors with advantages in challenging visual conditions, but state-of-the-art frame-based methods cannot be easily adapted to event data due to the limitations of current event simulators. We introduce a novel self-supervised loss combining the Contrast Maximization framework with a non-linear motion prior in the form of pixel-level trajectories and propose an efficient solution to solve the high-dimensional assignment problem between non-linear trajectories and events. Their effectiveness is demonstrated in two scenarios: In dense continuous-time motion estimation, our method improves the zero-shot performance of a synthetically trained model on the real-world dataset EVIMO2 by 29%. In optical flow estimation, our method elevates a simple UNet to achieve state-of-the-art performance among self-supervised methods on the DSEC optical flow benchmark. Our code is available at https://github.com/tub-rip/MotionPriorCMax.

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。

↑