AI Paper Atlas

Research map / 3D vision / Human pose estimation

PiLoT: Neural Pixel-to-3D Registration for UAV-based Ego and Target Geo-localization

Xiaoya Cheng, Long Wang, Yan Liu, Xinyi Liu, Hanlin Tan, Yu Liu, Maojun Zhang, Shen Yan

CVPR 2026 · 3D vision › Human pose estimation · approach: Learned camera pose estimation · 3 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 domain-specific training on synthetic UAV data to off-the-shelf backbone (ablation)PiLoT · Ablation, 10m/10deg initRecall@1m/1deg (%): 0.0 -> 15.2Improved
add rotation-aware hypothesis generation (ablation)PiLoT · Ablation, 10m/10deg initRecall@1m/1deg (%): 15.2 -> 70.6Improved
add motion regularizer for hypothesis selection (ablation)PiLoT · Ablation, 10m/10deg initRecall@1m/1deg (%): 70.6 -> 84.2Improved
train on synthetic data with light/weather instead of without (ablation)PiLoT · Ablation, 3m/3deg initRecall@1m/1deg (%): 63.5 -> 84.3Improved
train on synthetic data instead of MegaDepth only (ablation)PiLoT · Ablation, 3m/3deg initRecall@1m/1deg (%): 69.9 -> 84.3Improved
use PiLoT instead of Render2Loc (LoFTR)localization baseline · UAVD4L-2yr (zero-shot)median translation error (m): 1.08 -> 0.92Improved
use PiLoT instead of best baseline on SynthCity-6Render2Loc (RoMaV2) · SynthCity-6median translation error (m): 0.47 -> 0.46Improved
use PiLoT instead of Render2Loc for target geo-localizationRender2Loc · single-target realRecall@1m (%): 87.62 -> 90.81Improved
use PiLoT for target geo-localization in multi-target syntheticRender2Loc · multi-target syntheticRecall@1m (%): 89.03 -> 93.74Improved
use PiLoT instead of Render2Loc (LoFTR) at R@1 on UAVScenesRender2Loc (LoFTR) · UAVScenes (zero-shot)Recall@1m/1deg (%): 23.2 -> 25.5Mixed

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