AI Paper Atlas

Research map / Video / Video segmentation and tracking

MAVFusion: Efficient Infrared and Visible Video Fusion via Motion-Aware Sparse Interaction

Xilai Li, Weijun Jiang, Xiaosong Li, Yang Liu, Hongbin Wang, Tao Ye, Huafeng Li, Haishu Tan

ECCV 2026 · Video › Video segmentation and tracking · approach: Learned optical flow estimation · 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 mask-guided dynamic/static separation instead of whole-image strong interaction (Full-DB) (ablation)MAVFusion · VTMOTQ_M: 0.9282 -> 0.9741Improved
add mask-guided dynamic/static separation instead of whole-image strong interaction (Full-DB) (ablation)MAVFusion · VTMOTMS2R: 0.9878 -> 0.8301Improved
add dynamic branch to static-only model (Full-SB) (ablation)MAVFusion · VTMOTMS2R: 0.9913 -> 0.8301Improved
add dynamic branch to static-only model (Full-SB) (ablation)MAVFusion · VTMOTQ_S: 0.8680 -> 0.8504Hurt
use correct mask logic rather than inverted mask (w/ IM) (ablation)MAVFusion · VTMOTQ_M: 0.7863 -> 0.9741Improved
use correct mask logic rather than inverted mask (w/ IM) (ablation)MAVFusion · VTMOTQ_AB/F: 0.6889 -> 0.7182Improved
use sparse attention instead of dense attention (w/o SA) (ablation)MAVFusion · VTMOTQ_M: 0.8351 -> 0.9741Improved
use sparse attention instead of dense attention (w/o SA) (ablation)MAVFusion · VTMOTMS2R: 0.9662 -> 0.8301Improved
add MAFM instead of UniVF alignment (w/o MAFM) (ablation)MAVFusion · VTMOTQ_M: 0.7820 -> 0.9741Improved
add MAFM instead of UniVF alignment (w/o MAFM) (ablation)MAVFusion · VTMOTMS2R: 0.9799 -> 0.8301Improved
use MAVFusion instead of UniVF video fusionMAVFusion · 640x480 efficiencyFLOPs (G): 2164.07 -> 123.37Improved
use MAVFusion instead of VideoFusionMAVFusion · 640x480 efficiencyFPS: 7.83 -> 14.16Improved

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