SparseGTN: Human Trajectory Forecasting with Sparsely Represented Scene and Incomplete Trajectories

In recent years, great progress has been made in forecasting human motion in crowded scenes. However, current methods are far from practical applications due to the unbearable high computation costs, especially for encoding scene context. In addition, neglecting the partially detected trajectories makes the predicted outcome deviate from the real trajectory distribution. To handle the aforementioned concerns, we propose to represent the scene context and partially observed trajectories with sparse graphs. Customized for this special data structure, we design a hierarchical Graph Transformer Network model SparseGTN to predict multiple possible future trajectories of the target pedestrian by digesting the sparsely represented inputs. Our approach exhibits superiority over the state-of-the-art (SOTA) methods, utilizing a mere 3.42% of the number of floating point operations (FLOPs) and 0.53% of the number of model parameters. The code will be available online<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">⋆</sup>.