AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

Fusion in Your Way: Aligning Image Fusion with Heterogeneous Demands via Direct Preference Optimization

Weijian Su, Songqian Zhang, Yuqi Han, Jian Zhuang, Yongdong Huang, Qiang Zhang

CVPR 2026 · Image generation › Text-to-image diffusion · approach: Fairness and bias in generative models · 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
use joint conditional loss instead of single-objective L_ST (ablation)PALDM · LLVIPSD: 58.215 -> 60.806Improved
use joint conditional loss instead of multi-objective L_ET (ablation)PALDM · LLVIPSD: 53.612 -> 60.806Improved
use IDPO instead of standard DPO (ablation)PCLDM · LLVIPSD: 57.089 -> 61.911Improved
use IDPO instead of contrastive preference loss (ablation)PCLDM · LLVIPSD: 51.077 -> 61.911Improved
use IDPO instead of standard DPO (ablation)PCLDM · LLVIPAG: 14.215 -> 5.977Hurt
use IDPO instead of contrastive preference loss (ablation)PCLDM · LLVIPCNNIQA: 0.694 -> 0.655Hurt
add IDPO fine-tuning with segmentation preferences (ablation)PCLDM · MSRS segmentationmIoU: 55.21 -> 55.96Improved
use IDPO instead of standard DPO (ablation)PCLDM · MSRS segmentationmIoU: 55.20 -> 55.96Improved
add IDPO fine-tuning with segmentation preferences (ablation)PCLDM · MSRS segmentationmAcc: 63.52 -> 64.26Improved
add RLHF human-preference IDPO fine-tuning (ablation)PALDM · LLVIPSD: 60.806 -> 61.911Improved
add RLHF human-preference IDPO fine-tuning (ablation)PALDM · RoadSceneSD: 45.137 -> 40.535Hurt
add RLVF VLM-preference IDPO fine-tuning (ablation)PALDM · RoadSceneSD: 45.137 -> 53.323Improved

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