AGMA: Adaptive Gaussian Mixture Anchors for Prior-Guided Multimodal Human Trajectory Forecasting

arXiv:2602.04204v2 Announce Type: replace Abstract: Human trajectory forecasting requires capturing the multimodal nature of pedestrian behavior. However, existing approaches suffer from prior misalignment. Their learned or fixed priors often fail to capture the full distribution of plausible futures, limiting both prediction accuracy and diversity. We theoretically establish that prediction error is lower-bounded by prior quality, making prior modeling a key performance bottleneck. Guided by this insight, we propose AGMA (Adaptive Gaussian Mixture Anchors), which constructs expressive priors through two stages: extracting diverse behavioral patterns from training data and distilling them into a scene-adaptive global prior for inference. Extensive experiments on ETH-UCY, Stanford Drone, and JRDB datasets demonstrate that AGMA achieves state-of-the-art performance, confirming the critical role of high-quality priors in trajectory forecasting.

PANC: Prior-Aware Normalized Cut via Anchor-Augmented Token Graphs
ReaLiTy and LADS: A Unified Framework and Dataset Suite for LiDAR Adaptation Across Sensors and Adverse Weather Conditions
Fall Risk and Gait Analysis in Community-Dwelling Older Adults using World-Spaced 3D Human Mesh Recovery
ChangeBridge: Spatiotemporal Image Generation with Multimodal Controls for Remote Sensing

Source: arXiv cs.CV | 2026-04-15

Related