On Argoverse 2, a conditional variational autoencoder jointly predicts multiple vehicles' futures more accurately than recombined marginal predictions or scene-level-loss models, though with higher predicted collision rates.
SceneMotion: From Agent-Centric Embeddings to Scene-Wide Forecasts
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Self-driving vehicles rely on multimodal motion forecasts to effectively interact with their environment and plan safe maneuvers. We introduce SceneMotion, an attention-based model for forecasting scene-wide motion modes of multiple traffic agents. Our model transforms local agent-centric embeddings into scene-wide forecasts using a novel latent context module. This module learns a scene-wide latent space from multiple agent-centric embeddings, enabling joint forecasting and interaction modeling. The competitive performance in the Waymo Open Interaction Prediction Challenge demonstrates the effectiveness of our approach. Moreover, we cluster future waypoints in time and space to quantify the interaction between agents. We merge all modes and analyze each mode independently to determine which clusters are resolved through interaction or result in conflict. Our implementation is available at: https://github.com/kit-mrt/future-motion
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
From Marginal to Joint Predictions: Evaluating Scene-Consistent Trajectory Prediction Approaches for Automated Driving
On Argoverse 2, a conditional variational autoencoder jointly predicts multiple vehicles' futures more accurately than recombined marginal predictions or scene-level-loss models, though with higher predicted collision rates.