AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

SparScene: Efficient Traffic Scene Representation via Sparse Graph Learning for Large-Scale Trajectory Generation

Xiaoyu Mo, Jintian Ge, Zifan Wang, Chen Lv, Karl Henrik Johansson

TPAMI 2026 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Interactive multi-agent trajectory prediction · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add TiL module to L2A-only variant (ablation)SparScene (AL+G2) · WOMD val (20% train)minFDE@8s (m): 3.28 -> 2.89Improved
add A2A interaction module (ablation)SparScene (AL+G12) · WOMD val (20% train)minFDE@8s (m): 2.89 -> 2.73Improved
enlarge A2L radius from 5 to 10 (ablation)SparScene · WOMD val (20% train)minFDE@8s (m)Improved
enlarge A2L radius from 10 to 30 and 50 (ablation)SparScene · WOMD val (20% train)minFDE@8s (m)No clear effect
use dense three-hop omnidirectional search (OOO) instead of OFF (ablation)SparScene · WOMD val (20% train), r=10minFDE@8s (m): 2.77 -> 2.78No clear effect
use OFF search instead of purely forward (F, FFF) or one-step omnidirectional (O) (ablation)SparScene · WOMD val (20% train), r=10minFDE@8s (m): 2.77Improved
scene-level single-pass generation vs per-agent MTR++ as agents grow from 8 to 32SparScene · WOMD val (scaling, focal agents)latency (ms): 77 -> 118 (MTR++) vs 5 -> 5 (SparScene)Improved
sparse lightweight scene graph vs MTR++SparScene · WOMD testlatency (ms): 118 ms -> 5 ms; 86.6 M -> 3.2 M paramsImproved
sparse scene graph vs MTR++ on accuracySparScene · WOMD testMR: 0.1298 -> 0.1559Hurt
share encoded context across agents (symmetric encoder, MTR to MTR+)MTR · WOMD val (scaling, focal agents)latency (ms): 193 ms -> 98 ms; 15.6 GB -> 4.7 GBImproved
batch scenes into larger graph up to 5,620 agentsSparScene · Regional scaling (batched WOMD scenes)latency (ms): 5 -> 54Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy