AI Paper Atlas

Research map / 3D vision / Depth and stereo

Rectified Embedding Flow Learning for Aerial Multi-view Geo-localization

Hao Ruan, Jinliang Lin, Yingxin Lai, Zhiming Luo, Shaozi Li, Yu Zang, Cheng Wang

ECCV 2026 · 3D vision › Depth and stereo · approach: Cost-volume multi-view stereo · 0 citations (OpenAlex)

Read the paper

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 REFL (flow learning + embedding rectification)Qwen3-VL-Embedding-2B · Aerial MVGL (10 sub-tasks avg)R@1 (%): 40.77 -> 44.83Improved
add REFLQwen3-VL-Embedding-2B · Aerial MVGL (10 sub-tasks avg)R@10 (%): 62.29 -> 65.85Improved
add Stage 1 velocity-prior flow learning (100k steps) (ablation)REFL · Aerial MVGLmR@1 (%): 42.95 -> 44.41Improved
extend Stage 1 training from 100k to 400k steps (ablation)REFL · Aerial MVGLmR@1 (%): 44.41 -> 44.83Improved
use 6-layer instead of 1-layer velocity MLP (ablation)REFL · Aerial MVGLmR@1 (%): 43.89 -> 44.83Improved
use 6-layer instead of 4-layer velocity MLP (ablation)REFL · Aerial MVGLmR@1 (%): 43.45 -> 44.83Mixed
replace static contrastive learning with trajectory-guided rectification (ER-CL) (ablation)REFL · Aerial MVGLmR@1 (%): 40.77 -> 42.84Improved
add Stage 1 prior and joint L_FL to ER-CL (ablation)REFL · Aerial MVGLmR@1 (%): 42.84 -> 44.83Improved
add Stage 1 flow learning without contrastive supervision (ablation)Backbone (zero-shot) · Aerial MVGLmR@1 (%): 19.91 -> 16.15Hurt
add Stage 1 prior before static contrastive learning (ablation)Static contrastive baseline · Aerial MVGLmR@1 (%): 40.77 -> 37.31Hurt
set joint loss weight lambda to 0.5 instead of 0 (ablation)REFL · Aerial MVGLmR@1 (%): 43.06 -> 44.83Improved
set joint loss weight lambda to 0.5 instead of 1.0 (ablation)REFL · Aerial MVGLmR@1 (%): 43.82 -> 44.83Improved

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