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 2112.01641cs.CVcs.AIcs.LG
收藏

图像序列中内容和运动解纠缠的Hamilton隐算子

Hamiltonian latent operators for content and motion disentanglement in image sequences

University of Edinburgh(爱丁堡大学)

Asif Khan, Amos Storkey

摘要:

我们介绍了\textit{HALO} --一种深度生成模型,利用Hamiltonian潜在算子来可靠地解开图像序列中的内容和运动信息。\textit{content}表示序列的汇总统计量,而\textit{motion}是一个动态过程,用于确定如何在序列的任何部分中表达信息。通过将动力学建模为哈密尔顿运动,确保了重要的必要条件:(1)运动是可逆的,(2)相空间中的辛,保体积结构意味着路径是连续的,并且在潜在空间中不发散。因此,序列帧的接近性是通过它们在相空间中的坐标的接近性来实现的,这对于解纠缠和长时间序列的产生是有价值的。序列空间通常由不同类型的动力学运动组成。为了确保长期可分性并允许受控生成,我们将每个运动与作用在其各自子空间中的唯一哈密顿量相关联。我们证明了\textit{HALO}的效用交换的一对序列,控制生成,和图像旋转的运动。

英文摘要:

We introduce \textit{HALO} -- a deep generative model utilising HAmiltonian Latent Operators to reliably disentangle content and motion information in image sequences. The \textit{content} represents summary statistics of a sequence, and \textit{motion} is a dynamic process that determines how information is expressed in any part of the sequence. By modelling the dynamics as a Hamiltonian motion, important desiderata are ensured: (1) the motion is reversible, (2) the symplectic, volume-preserving structure in phase space means paths are continuous and are not divergent in the latent space. Consequently, the nearness of sequence frames is realised by the nearness of their coordinates in the phase space, which proves valuable for disentanglement and long-term sequence generation. The sequence space is generally comprised of different types of dynamical motions. To ensure long-term separability and allow controlled generation, we associate every motion with a unique Hamiltonian that acts in its respective subspace. We demonstrate the utility of \textit{HALO} by swapping the motion of a pair of sequences, controlled generation, and image rotations.

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。

↑