arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.14727cs.CVcs.LG
收藏

基于时空迭代推理的无监督视频分解

Unsupervised Video Decomposition using Spatio-temporal Iterative Inference

University of British Columbia(不列颠哥伦比亚大学);Borealis AI;Vector Institute for AI(Vector AI研究所)

Polina Zablotskaia, Edoardo A. Dominici, Leonid Sigal, Andreas M. Lehrmann

摘要:

无监督多目标场景分解是表示学习中的一个新兴问题。尽管在静态场景中取得了重大进展,但这些模型无法利用视频中存在的重要动态线索。我们提出了一种新的时空迭代推理框架,该框架足够强大,可以联合建模复杂的多对象表示和跨帧隐变量之间的显式时间依赖关系。这是通过利用2D-LSTM,时间条件推理和迭代摊销推理中的生成来实现的。我们的方法提高了分解的整体质量,编码有关对象动态的信息,并可用于单独预测每个对象的轨迹。此外,我们表明,我们的模型具有很高的准确性,即使没有颜色信息。我们展示了我们的模型的分解,分割和预测能力,并表明它在几个基准数据集上的表现优于最先进的技术,其中一个是为这项工作策划的,并将公开提供。

英文摘要:

Unsupervised multi-object scene decomposition is a fast-emerging problem in representation learning. Despite significant progress in static scenes, such models are unable to leverage important dynamic cues present in video. We propose a novel spatio-temporal iterative inference framework that is powerful enough to jointly model complex multi-object representations and explicit temporal dependencies between latent variables across frames. This is achieved by leveraging 2D-LSTM, temporally conditioned inference and generation within the iterative amortized inference for posterior refinement. Our method improves the overall quality of decompositions, encodes information about the objects' dynamics, and can be used to predict trajectories of each object separately. Additionally, we show that our model has a high accuracy even without color information. We demonstrate the decomposition, segmentation, and prediction capabilities of our model and show that it outperforms the state-of-the-art on several benchmark datasets, one of which was curated for this work and will be made publicly available.

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。

↑