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.
Vectornet: Encoding hd maps and agent dynamics from vectorized representation,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
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.