AI Paper Atlas

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

MMVIP: A Visible-infrared Paired Dataset for Multi-weather Marine Vision

Yunpeng Yin, Lihan Wang, Zhaoshen He, Xinqiang He, Xingming Liao, Zhuowei Wang, Lianglun Cheng

CVPR 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modality image fusion

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 fine-tuned MINIMA with RoMa (dense matching) instead of sparse or semi-dense matchersvisible-infrared registration · MMVIP registrationMSE / SSIM: MSE 0.0039, SSIM 0.8822 (best of nine methods)Improved
use dense matching instead of sparse matching in terms of runtimeregistration time · MMVIP registrationtime (ms): MINIMA_LG 480.8 -> RoMa 5042.6Hurt
switch from visible to infrared images for ship detectionYOLO11 · MMVIP ship detectionmAP@0.5:0.95: 0.754 -> 0.590Hurt
switch from visible to infrared images for buoy detectionYOLO11 · MMVIP buoy detectionmAP@0.5: 0.795 -> 0.599Hurt
switch from visible to infrared images for buoy precisionYOLO11 · MMVIP buoy detectionprecision: 0.874 -> 0.889Improved
low-light, night and foggy conditions for registrationregistration algorithms · MMVIP registrationqualitative registration qualityHurt
rainy weather for infrared detectionYOLO11 infrared · MMVIP detectionqualitative detectionHurt

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