AI Paper Atlas

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

Towards Unified Semantic and Controllable Image Fusion: A Diffusion Transformer Approach

Jiayang Li, Chengjie Jiang, Junjun Jiang, Pengwei Liang, Jiayi Ma, Liqiang Nie

TPAMI 2025 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modality image fusion · 14 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 noise-mask and Gaussian-noise degradations to blur-only M3 (ablation)DiTFuse · MSRS (IVIF)PSNR: 65.58 -> 66.63Improved
add blur and Gaussian-noise degradations to noise-mask-only M3 (ablation)DiTFuse · MSRS (IVIF)PSNR: 65.48 -> 66.63Improved
add blur and noise-mask degradations to Gaussian-noise-only M3 (classical MIM) (ablation)DiTFuse · MSRS (IVIF)CLIP-IQA+: 0.257 -> 0.392Improved
add blur and noise-mask degradations to Gaussian-noise-only M3 (classical MIM) (ablation)DiTFuse · MSRS (IVIF)MUSIQ: 31.09 -> 36.28Improved
add explicit task and subtask tags to training instructions (ablation)DiTFuse · fusion and control qualitativecolor fidelity and subtask controllabilityImproved
combine M3 data with fusion data (vs fusion-only) (ablation)DiTFuse · IVIF qualitativevisual qualityImproved
add fusion data to M3-only training (ablation)DiTFuse · IVIF qualitativeartifactsImproved
keep task tag at test time (vs removing it) (ablation)DiTFuse · brightness control qualitativebrightness enhancement intensityImproved
use standardized prompt template (vs removing template / noisy prompts) (ablation)DiTFuse · noisy prompt qualitativefusion quality and controllabilityImproved
DiTFuse text-controlled segmentation vs LISA on fused imageDiTFuse · FMB segmentationoverall mIoU: 0.4386 -> 0.4760Improved
DiTFuse vs LISA on road class by GPT-4o precision ratioDiTFuse · M3FD (GPT-4o seg eval)P.Ratio: 0.25 -> 0.84Improved
DiTFuse vs LISA on person class by GPT-4o precision ratioDiTFuse · SICE (GPT-4o seg eval)P.Ratio: 0.12 -> 0.43Improved

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