AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Mind the Gap: Aligning Vision Foundation Models to Image Feature Matching

Yuhan Liu, Jingwen Fu, Yang Wu, Kangyi Wu, Pengna Li, Jiayi Wu, Sanping Zhou, Jingmin Xin

ICCV 2025 · Vision-language and multimodal › Cross-modal learning · approach: Contrastive vision-language alignment · 5 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 Stable Diffusion features instead of Swin (B) (ablation)IMD · IMIMmatching accuracy (%): 74.0 -> 88.7Improved
use Stable Diffusion features instead of DINOv2 (B) (ablation)IMD · IMIMmatching accuracy (%): 75.5 -> 88.7Improved
use Stable Diffusion features instead of DINOv2 (B) (ablation)IMD · MegaDepthAUC@5: 57.8 -> 61.2Improved
use Stable Diffusion features instead of Swin (B) (ablation)IMD · MegaDepthAUC@5: 57.5 -> 61.2Improved
add CIPM prompt instead of an empty string (ablation)IMD · IMIMmatching accuracy (%): 84.0 -> 88.7Improved
add CIPM prompt instead of an empty string (ablation)IMD · MegaDepthAUC@5: 58.4 -> 61.2Improved
use cross-image prompt instead of individual image prompt (ablation)IMD · IMIMmatching accuracy (%): 85.2 -> 88.7Improved
use cross-image prompt instead of individual image prompt (ablation)IMD · MegaDepthAUC@5: 59.6 -> 61.2Improved
add cross attention in CIPM instead of concatenation with shared prompt (ablation)IMD · IMIMmatching accuracy (%): 87.4 -> 88.7Improved
add cross attention in CIPM instead of concatenation with shared prompt (ablation)IMD · MegaDepthAUC@5: 60.7 -> 61.2Improved
extract features at t = 0 instead of t = 100 (ablation)IMD · IMIMmatching accuracy (%): 88.1 -> 88.7Improved
extract features at t = 0 instead of t = 100 (ablation)IMD · MegaDepthAUC@5: 60.9 -> 61.2Improved

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