AI Paper Atlas

Research map / 3D vision / Depth and stereo

Beyond Tie Points: Satellite Image Block Adjustment based on Dense Feature Consistency

Yi Liu, Yi Wan, Lei Yu, Panwang Xia, Qiong Wu, Yingying Pei, Xuejun Huang, Junjian Zhang, Xiangyuan Cai, Hongwei Hu, Yongjun Zhang

CVPR 2026 · 3D vision › Depth and stereo · approach: Camera model and calibration for SfM

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 geographic-coordinate-regression adapter to frozen features (ablation)Ours · Guangzhou-b (ablation)mean error (m): 5.57 -> 4.66Improved
add confidence weighting without adapter (ablation)Ours · Guangzhou-b (ablation)mean error (m): 5.57 -> 5.55No clear effect
add confidence weighting on top of adapter (ablation)Ours · Guangzhou-b (ablation)mean error (m): 4.66 -> 1.84Improved
add confidence weighting on top of adapter (ablation)Ours · Guangzhou-b (ablation)percentage within 3 m: 18.33 -> 88.33Improved
use dense feature consistency instead of tie points (vs PBA-LoFTR)Ours · Beijing small initial errormean error (m): 5.87 -> 2.24Improved
use dense feature consistency instead of tie points (vs PBA-LoFTR)Ours · Guangzhou small initial errormean error (m): 5.06 -> 1.42Improved
add confidence filtering to LoFTR tie pointsPBA-LoFTR · Beijing small initial errormean error (m): 5.87 -> 4.03Improved
use full method instead of LoFTR with confidence filteringOurs · Beijing small initial errormean error (m): 4.03 -> 2.24Improved
use full method instead of LoFTR with confidence filteringOurs · San Jose large initial errormean error (m): 0.56 -> 0.75Hurt
use full method on San Jose small initial errorOurs · San Jose small initial errormean error (m): 0.53 -> 0.50Improved

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