AI Paper Atlas

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

MUSE-VAE: Multi-Scale VAE for Environment-Aware Long Term Trajectory Prediction

Mihee Lee, Samuel S. Sohn, Seonghyeon Moon, Sejong Yoon, Mubbasir Kapadia, Vladimir Pavlovic

CVPR 2022 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Interactive multi-agent trajectory prediction · 80 citations (OpenAlex)

Check 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
Use MUSE-VAE instead of the strongest baselinePFSD (K=50) · PFSDKDE NLL: 1.17 -> -1.94Improved
Use MUSE-VAE instead of the strongest baselinePFSD (K=50) · PFSDADE: 0.08 -> 0.07Mixed
Use MUSE-VAE instead of the strongest baselineSDD (K=20) · SDDADE: 7.84 -> 6.36Improved
Use MUSE-VAE instead of the strongest baselineSDD (K=20) · SDDECFL: 89.32 -> 89.30No clear effect
Use MUSE-VAE instead of the strongest baselinenuScenes (K=10) · nuScenesADE: 1.30 -> 1.09Improved
Add SG-net waypoint predictions (ablation)MUSE-VAE · PFSD (K=20)KDE NLL: -1.39 -> -1.66Improved
Add SG-net waypoint predictions (ablation)MUSE-VAE · PFSD (K=20)ADE: 0.10 -> 0.09No clear effect
Add Micro-stage trajectory refinement (ablation)MUSE-VAE · PFSD (K=20)ECFL: 99.75 -> 97.40Hurt
Add Micro-stage trajectory refinement (ablation)MUSE-VAE · PFSD (K=20)ADE: 0.10 -> 0.09Improved
Add prior-distribution reconstruction loss (ablation)MUSE-VAE · PFSD (K=20)ECFL: 95.06 -> 97.40Improved
Add prior-distribution reconstruction loss (ablation)MUSE-VAE · PFSD (K=20)KDE NLL: -1.77 -> -1.66Hurt

Later papers that compared with this method

1 later accepted paper reports MUSE-VAE as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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