Paper Detail

FutureLift: Lifting Trajectory Proposals into Bidirectional Future Graphs for Motion Forecasting

Daniel Grimm, J. Marius Zöllner

arxiv Score 9.8

Published 2026-10-15 · First seen 2026-10-16

General AI

Abstract

Accurate motion prediction is critical for safe autonomous driving, yet even strong forecasters leave residual errors in their multimodal proposals. Existing refiners compress complete proposals or update their segments sequentially, preventing the full proposed future from serving as explicit relational context for correction. We introduce FutureLift, a backbone-agnostic refiner that represents each multimodal proposal as a heterogeneous future graph, with spatially grounded temporal nodes connected to agent histories, map elements, alternative modes, and, for joint prediction, other agents future trajectories. Bidirectional temporal edges allow later evidence to revise earlier segments in a single pass, and the updated nodes predict residual coordinate and confidence corrections. Requiring only proposals, scores, and scene context, FutureLift provides a common refinement interface for structurally different forecasting backbones. On Argoverse2 and the Waymo Open Motion Dataset, it consistently improves frozen proposals and outperforms native and specialized refiners across marginal and joint forecasting. On the WOMD motion-prediction leaderboard, FutureLift ranks first in minADE (0.5049m) and minFDE (0.9942m) among the compared standard-input methods, without LiDAR or ensembling, while achieving a competitive 0.4874 Soft mAP.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{grimm2026futurelift,
  title = {FutureLift: Lifting Trajectory Proposals into Bidirectional Future Graphs for Motion Forecasting},
  author = {Daniel Grimm and J. Marius Zöllner},
  year = {2026},
  abstract = {Accurate motion prediction is critical for safe autonomous driving, yet even strong forecasters leave residual errors in their multimodal proposals. Existing refiners compress complete proposals or update their segments sequentially, preventing the full proposed future from serving as explicit relational context for correction. We introduce FutureLift, a backbone-agnostic refiner that represents each multimodal proposal as a heterogeneous future graph, with spatially grounded temporal nodes conn},
  url = {https://arxiv.org/abs/2610.22215},
  keywords = {cs.CV, cs.LG},
  eprint = {2610.22215},
  archiveprefix = {arXiv},
}

Metadata

{}