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 2207.04007cs.CVcs.ROmath.DG
收藏

对比度最大化框架中的事件坍缩

Event Collapse in Contrast Maximization Frameworks

Keio University(庆应义塾大学);Technische Universität Berlin(柏林工业大学);Einstein Center Digital Future(爱因斯坦数字未来中心)

Shintaro Shiba, Yoshimitsu Aoki, Guillermo Gallego

AI总结:

针对对比度最大化框架中的事件坍缩问题,本文基于微分几何与物理的时空变形第一性原理提出坍缩度量,并在公开数据集上验证其正则化可缓解坍缩且不损害适定扭曲。

摘要:

对比度最大化(Contrast maximization,CMax)是一个在若干基于事件的计算机视觉任务(如自运动或光流估计)上提供最先进结果的框架。然而,它可能受到一个称为事件坍缩的问题影响,这是一种不希望出现的解,其中事件被扭曲到过少的像素中。由于以往的工作在很大程度上忽视了这一问题,或只是提出了一些权宜之计,因此有必要详细分析这一现象。我们的工作展示了其最简单形式的事件坍缩,并利用基于微分几何和物理学的时空变形第一性原理,提出了坍缩度量。我们在公开可用的数据集上通过实验表明,所提出的度量能够缓解事件坍缩,并且不会损害适定的扭曲。据我们所知,在所考虑的实验设置中,与其他方法相比,基于所提度量的正则化项是对抗事件坍缩的唯一有效解决方案。我们希望这项工作能启发进一步研究,以处理更复杂的扭曲模型。

英文摘要:

Contrast maximization (CMax) is a framework that provides state-of-the-art results on several event-based computer vision tasks, such as ego-motion or optical flow estimation. However, it may suffer from a problem called event collapse, which is an undesired solution where events are warped into too few pixels. As prior works have largely ignored the issue or proposed workarounds, it is imperative to analyze this phenomenon in detail. Our work demonstrates event collapse in its simplest form and proposes collapse metrics by using first principles of space-time deformation based on differential geometry and physics. We experimentally show on publicly available datasets that the proposed metrics mitigate event collapse and do not harm well-posed warps. To the best of our knowledge, regularizers based on the proposed metrics are the only effective solution against event collapse in the experimental settings considered, compared with other methods. We hope that this work inspires further research to tackle more complex warp models.

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。

↑