AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

Fast Inference and Update of Probabilistic Density Estimation on Trajectory Prediction

Takahiro Maeda, Norimichi Ukita

ICCV 2023 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Expressive invertible architectures · 62 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
reuse flow transformations and update with newest observed position instead of re-predicting from scratch (rapid update) (ablation)FlowChain · ETH/UCY log-probability t+6..t+12log-probability: -0.26 -> 0.31Improved
update density from t-1 instead of predicting at tFlowChain · SimforkEMD: 1.408 -> 2.539Hurt
update density instead of full prediction (compute time)FlowChain · ETH/UCYcomputation time (ms): 37.0 -> 0.6Improved
use continuously-indexed flows instead of vanilla conditional flows (ablation)FlowChain · ETH/UCY ADEADE (m): 0.35 -> 0.29Improved
use continuously-indexed flows instead of vanilla conditional flows (ablation)FlowChain · SDD ADEADE (pixels): 9.70 -> 9.93No clear effect
use continuously-indexed flows for density estimation (ablation)FlowChain · SimforkEMD: 3.313 -> 1.408Improved
use RealNVP instead of MAF (ablation)FlowChain · SDD ADEADE (pixels): 14.58 -> 9.93Improved
use Trajectron++ social encoder instead of a per-agent transformer layer (ablation)FlowChain · SDD ADEADE (pixels): 18.92 -> 9.93Improved
analytic normalizing-flow density instead of Gaussian mixture (Trajectron++)trajectory density estimation · ETH/UCYlog-probability: -281.86 -> -0.26Improved
analytic flow density instead of KDE on sampled trajectories (MID)trajectory density estimation · ETH/UCYcomputation time (ms): 23904.1 -> 37.0Improved

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