AI Paper Atlas

Research map / Video / Video generation

Streaming Diffusion Model for Fast Infrared and Visible Video Fusion

Jinyuan Liu, Ludan Sun, Tengyu Ma, Chunyan Yang, Zhiying Jiang, Long Ma, Risheng Liu, Xin Fan

CVPR 2026 · Video › Video generation · approach: Efficient video diffusion models

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 temporal feature propagation (flow-aligned memory injection) (ablation)SDMFusion · M3SVDVIF: 0.873 -> 0.926Improved
add temporal feature propagation (flow-aligned memory injection) (ablation)SDMFusion · VTMOTSCD: 1.569 -> 1.583Improved
add temporal aggregation adapter after U-Net decoder (vs standard convolution) (ablation)SDMFusion · M3SVDVIF: 0.897 -> 0.926Improved
add temporal aggregation adapter after U-Net decoder (vs standard convolution) (ablation)SDMFusion · VTMOTSCD: 1.562 -> 1.583Improved
add temporal consistency loss (ablation)SDMFusion · M3SVDVIF: 0.920 -> 0.926Improved
add temporal consistency loss (ablation)SDMFusion · VTMOTVIF: 1.018 -> 1.026No clear effect
use SDMFusion fused video as input to ByteTrack tracker instead of other fusion methodsSDMFusion · NOT-156 trackingAUC: 0.3774 -> 0.3799Improved
use one-step sampling streaming framework vs second-best competitorSDMFusion · VTMOTinference time: more than 1.42x fasterImproved

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