AI Paper Atlas

Research map / 3D vision / Depth and stereo

AerialMetric: Benchmarking and Adapting UAV Monocular Metric Depth Estimation in the Real World

Zhongqiang Song, Guanying Chen, Yuqi Zhang, Yin Zou, Chuanyu Fu, Zhiyuan Yuan, Chuan Huang, Shuguang Cui, Xiaochun Cao

ECCV 2026 · 3D vision › Depth and stereo · approach: Self-supervised monocular depth · 4 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
fine-tune MoGe2 on AerialMetricMoGe2 · AerialMetric-Oblique City (w/o GT intrinsics)delta1: 5.1 -> 89.3Improved
fine-tune MoGe2 on AerialMetricMoGe2 · AerialMetric-Wild (0-400m)AbsRel: 55.26 -> 21.34Improved
fine-tune MoGe2 on AerialMetricMoGe2 · AerialMetric-Wild (0-400m)delta1: 9.5 -> 53.7Improved
provide GT camera intrinsics at test timeMoGe2 · AerialMetric-Oblique Citydelta1: 5.1 -> 18.1Improved
fine-tune MoGe2 on AerialMetricMoGe2 · KITTI and ETH3D (ground, w/o GT intrinsics)delta1: KITTI 64.7 -> 68.7; ETH3D 88.8 -> 86.7Mixed
fine-tune MoGe2 on AerialMetricMoGe2 · HAMMER (w/o GT intrinsics)AbsRel: 26.0 -> 31.7Hurt
use full fine-tuning instead of LoRA r=96 (ablation)MoGe2 · Ground-domain meandelta1: 79.59 -> 56.70Hurt
use LoRA r=128 instead of r=96 (ablation)MoGe2 LoRA · Ground-domain meandelta1: 79.59 -> 69.40Hurt
update only scale head instead of LoRA r=96 (ablation)MoGe2 · AerialMetric-Obliquedelta1: 84.40 -> 53.00Hurt
add AerialMetric-Synthetic to Oblique training data (ablation)MoGe2 LoRA · AerialMetric-Decoupled (mean)delta1: 77.45 -> 84.20Improved
add AerialMetric-Synthetic to Oblique training data (ablation)MoGe2 LoRA · AerialMetric-Oblique (mean)delta1: 87.4 -> 82.30Hurt
add small fraction of ground-domain data (ablation)MoGe2 LoRA · ETH3Ddelta1: 71.54 -> 86.67Improved

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