In many real-world scenarios, such as single-cell RNA sequencing, data are observed only as discrete-time snapshots spanning finite time intervals and subject to noisy timestamps, with no continuous trajectories available. Recovering the underlying continuous-time dynamics from these snapshots with coarse and noisy observation times is a critical and challenging task. We propose Continuous-Time Optimal Transport Flow (CT-OT Flow), which first infers high-resolution time labels via partial optimal transport and then reconstructs a continuous-time data distribution through a temporal kernel smoothing. This reconstruction enables accurate training of dynamics models such as ODEs and SDEs. CT-OT Flow consistently outperforms state-of-the-art methods on synthetic benchmarks and achieves lower reconstruction errors on real scRNA-seq and typhoon-track datasets. Our results highlight the benefits of explicitly modeling temporal discretization and timestamp uncertainty, offering an accurate and general framework for bridging discrete snapshots and continuous-time processes.
View on arXiv@article{kawano2025_2505.17354,
title={ CT-OT Flow: Estimating Continuous-Time Dynamics from Discrete Temporal Snapshots },
author={ Keisuke Kawano and Takuro Kutsuna and Naoki Hayashi and Yasushi Esaki and Hidenori Tanaka },
journal={arXiv preprint arXiv:2505.17354},
year={ 2025 }
}