AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

DiffTraj: Generating GPS Trajectory with Diffusion Probabilistic Model

Yuanshao Zhu, Yongchao Ye, Shiyao Zhang, Xiangyu Zhao, James Yu

NeurIPS 2023 · Image generation › Fast diffusion sampling · approach: Guidance for conditional diffusion · 26 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 Wide & Deep conditional information embedding (ablation)DiffTraj · ChengduPattern score: 0.643 -> 0.823Improved
add Wide & Deep conditional information embedding (ablation)DiffTraj · ChengduDensity error: 0.0072 -> 0.0055Improved
use Traj-UNet instead of removing UNet (ablation)DiffTraj · ChengduDensity error: 0.0356 -> 0.0055Improved
use 1D-CNN Traj-UNet instead of WaveNet backbone (ablation)DiffTraj · ChengduDensity error: 0.0145 -> 0.0055Improved
use 1D-CNN Traj-UNet instead of LSTM backbone (ablation)DiffTraj · ChengduDensity error: 0.0068 -> 0.0055Improved
generate full trajectories instead of scattered locations (ablation)DiffTraj · ChengduDensity error: 0.0209 -> 0.0055Improved
use diffusion instead of VAEtrajectory generation · ChengduDensity error: 0.0148 -> 0.0055Improved
skip sampling steps to S=100 with T=500DiffTraj · sampling speedTime cost: saving 81% of the time costImproved
use fewer than 100 sampling stepsDiffTraj · sampling speedDensity errorHurt
pretrain on another city before training on 5% of dataDiffTraj · transfer learningDensity errorImproved
train prediction on DiffTraj-generated instead of real datainflow/outflow prediction · AGCRN inflowRMSE: 2.08 -> 2.13Hurt

Later papers that compared with this method

4 later accepted papers report DiffTraj as a baseline in their results tables; 4 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