AI Paper Atlas

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

SGPFeat: Semantic and Geometric Priors for Multi-modal Image Matching

Yuxin Deng, Botian Wang, Kaining Zhang, Hao Zhang, Jiayi Ma

AAAI 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modality image fusion · 0 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 semantic and geometric distillation losses to basic constraints (ablation)SGPFeat · VIS-NIR (1024 keypoints)SRR: 34.1 -> 81.1Improved
add semantic and geometric distillation losses (ablation)SGPFeat · VIS-NIR (1024 keypoints)Ravg (px): 6.10 -> 3.65Improved
add semantic and geometric distillation losses (ablation)SGPFeat · VIS-NIR (1024 keypoints)CLR (%): 10.6 -> 0Improved
add a single distillation loss to basic constraints (ablation)SGPFeat · VIS-NIR (1024 keypoints)SRR: 34.1 -> 45.5Improved
add two distillation losses (variant c) (ablation)SGPFeat · VIS-NIR (1024 keypoints)SRR: 34.1 -> 72.7Improved
add the third distillation loss on top of two (variant d to full) (ablation)SGPFeat · VIS-NIR (1024 keypoints)SRR: 71.2 -> 81.1Improved
replace ALIKE geometric teacher with RDD (ablation)SGPFeat · VIS-IRSRR: 87.2 -> 44.7Hurt
replace ALIKE geometric teacher with ALIKED (ablation)SGPFeat · VIS-IRRavg (px): 3.94 -> 4.23Hurt
train on VIS-IR instead of VIS-NIR for zero-shot transfer (ablation)SGPFeat · CT-MRI zero-shotSRR: 58.3 -> 79.2Improved
train on VIS-IR instead of VIS-NIR for zero-shot transfer (ablation)SGPFeat · EMA-OCTA zero-shotSRR: 40.0 -> 50.0Improved
use DINO V2 instead of DepthAnything V2 as semantic teacher (ablation)SGPFeat · VIS-NIRmatching accuracyHurt

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