AI Paper Atlas

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

LUT-Fuse: Towards Extremely Fast Infrared and Visible Image Fusion via Distillation to Learnable Look-Up Tables

Xunpeng Yi, Yibing Zhang, Xinyu Xiang, Qinglong Yan, Han Xu, Jiayi Ma

ICCV 2025 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modality image fusion · 26 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 low-order approximation encoding (ablation)LUT-Fuse · MFNetSSIM: 0.533 -> 0.966Improved
add contextual scene encoding (ablation)LUT-Fuse · MFNetSSIM: 0.553 -> 0.966Improved
add efficient MM-LUT distillation strategy (ablation)LUT-Fuse · MFNetSSIM: 0.904 -> 0.966Improved
add efficient MM-LUT distillation strategy (ablation)LUT-Fuse · MFNetQ^AB/F: 0.566 -> 0.628Improved
add low-order approximation encoding (ablation)LUT-Fuse · MFNetentropy: 6.574 -> 6.394Hurt
use learnable distillation LUT instead of quantization LUTTar-DAL · MFNetSSIM: 0.476 -> 0.745Improved
use learnable distillation LUT instead of quantization LUTDiff-IF · MFNetQ^AB/F: 0.202 -> 0.625Improved
use learnable distillation LUT instead of quantization LUTCDDFuse · MFNetSSIM: 0.553 -> 0.857Improved
distill MM-Net into MM-LUT (student) instead of using MM-NetLUT-Fuse · MFNetMI: 2.764 -> 2.560Hurt
use LUT-Fuse instead of Tar-DAL for fusion speedLUT-Fuse · MFNet runtime, RTX 4060 Titime (ms): 21.83 -> 4.70Improved
use LUT-Fuse instead of Tar-DAL on edge deviceLUT-Fuse · Jetson Orin NX 720Ptime (ms): 389.34 -> 30.54Improved
use LUT-Fuse fused images for segmentation instead of Text-IFLUT-Fuse · MFNet segmentationmIoU: 55.32 -> 54.82Mixed

Later papers that compared with this method

1 later accepted paper reports LutFuse as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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