AI Paper Atlas

Research map / Learning theory and algorithms / Optimal transport

2D Gaussians Spatial Transport for Point-supervised Density Regression

Miao Shang, Xiaopeng Hong

AAAI 2026 · Learning theory and algorithms › Optimal transport · approach: Neural optimal transport · 2 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
use heuristic Gaussian transport kernel instead of L2 direct regression (ablation)VGG counting model · JHU-Crowd++ (VGG)MAE: 81.70 -> 65.45Improved
derive transport kernel from 2D Gaussian splatting instead of heuristic (ablation)GST · JHU-Crowd++ (VGG)MAE: 65.45 -> 60.17Improved
add pixel-to-background correspondence (ablation)GST · JHU-Crowd++ (VGG)MAE: 60.17 -> 58.30Improved
replace OT loss with GST lossVGG counting model · UCF-QNRF (VGG)MAE: 87.2 -> 82.5Improved
replace OT loss with GST lossTransformer counting model · NWPU-CrowdMAE: 80.9 -> 74.4Improved
replace OT loss with GST (training time)VGG counting model · JHU-Crowd++ (VGG)training time: 28h36min -> 15h32minImproved
use GST instead of PET/APGCC on UCF-QNRFTransformer counting model · UCF-QNRFMAE: 79.5 -> 80.7Hurt
use ground-truth scale information for the plan instead of 2DGS scales (ablation)GST · JHU-Crowd++ (VGG)MAE: 58.30 -> 56.60Improved
use GST instead of HRNet direct regressionHRNet-W32 · MPII Human Posemean PCKh@0.5: 90.4 -> 91.0Improved
use GST instead of HRNet on head jointHRNet-W32 · MPII Human PoseHead PCKh@0.5: 97.1 -> 96.2Hurt

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