Trajectory data collected in real-world settings is frequently incomplete due to sensor failure, communication loss, or occlusion. This paper addresses the task of \emph{trajectory inpainting}: reconstructing contiguous missing segments from observed context. We propose a Temporal Convolutional Network (TCN) with symmetric dilation that relaxes the standard causality constraint, allowing each time step to draw on both past and future observations, a property that is essential for inpainting but absent from forecasting-oriented architectures.
The model is trained with a composite loss that combines weighted mean squared error, boundary–continuity penalties, and a smoothness regularizer. Trained on a synthetic dataset of (1,000) (train), (200) (validation), and (300) (test) two-dimensional trajectories with randomly placed 20% masked segments, the model achieves good R², MSE, and MAE metrics.
Blogger's Review: This paper provides an innovative approach to trajectory data inpainting, overcoming the limitations of traditional forecasting models through the design of temporal convolutional networks, demonstrating significant practical value.