AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

Towards Metric-Agnostic Trajectory Forecasting

Markus Knoche, Daan de Geus, Bastain Leibe

ECCV 2026 · Probabilistic and scientific modeling › Molecules and proteins · approach: Multimodal trajectory prediction · 0 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
apply window policy to Step-NLL predictions (instead of naive output)DONUT Step-NLL (Laplace) · Waymo valSoft mAP: 0.3595 -> 0.5082Improved
apply distance policy to Step-NLL predictionsDONUT Step-NLL (Laplace) · Waymo valminFDE: 1.2236 -> 1.0200Improved
apply distance policy to WTA-trained predictionsDONUT WTA · Waymo valminFDE: 1.0520 -> 1.0824Hurt
replace WTA loss with Step-NLL when policies are applied (ablation)DONUT · Waymo valSoft mAP: 0.4764 -> 0.5082Improved
replace WTA loss with Traj-NLL when policies are applied (ablation)DONUT · Waymo valminFDE: 1.0824 -> 1.0374Improved
replace WTA loss with Step-NLL under naive evaluation (ablation)DONUT · Waymo valminFDE: 1.0520 -> 1.2236Hurt
replace Laplace with generalized Gaussian position distribution (with policies) (ablation)DONUT Step-NLL · Waymo valSoft mAP: 0.5082 -> 0.5101Improved
replace Laplace with generalized Gaussian (distance policy) (ablation)DONUT Step-NLL · Waymo valminFDE: 1.0200 -> 1.0103Improved
replace Laplace with Gaussian scale mixture under naive evaluation (ablation)DONUT Step-NLL · Waymo valSoft mAP: 0.3595 -> 0.3837Improved
replace Laplace with Gaussian scale mixture (window policy) (ablation)DONUT Step-NLL · Waymo valSoft mAP: 0.5082 -> 0.5053Hurt
apply policies to MTR with WTA loss (vs original NMS outputs)MTR · Waymo valSoft mAP: 0.4288 -> 0.4837Improved
apply distance policy to QCNet WTA predictionsQCNet · Waymo valminFDE: 1.2254 -> 2.2805Hurt

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