AI Paper Atlas

Research map / Image generation / Editing and style transfer

DreamFuse: Adaptive Image Fusion with Diffusion Transformer

Junjia Huang, Pengxiang Yan, Jiyang Liu, Jie Wu, Zhao Wang, Yitong Wang, Liang Lin, Guanbin Li

ICCV 2025 · Image generation › Editing and style transfer · approach: Inversion-based diffusion editing · 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
use positional affine instead of direct transform for foreground position (ablation)DreamFuse first stage · DreamFuse test setVisionReward: 4.72 -> 5.28Improved
use positional affine instead of mask tokenizer (ablation)DreamFuse first stage · DreamFuse test setVisionReward: 4.93 -> 5.28Improved
use positional affine instead of direct transform (ablation)DreamFuse first stage · DreamFuse test setCLIP: 35.04 -> 35.22Improved
add LDPO second-stage preference optimization on seed pairs (ablation)DreamFuse · DreamFuse test setImageReward: 1.07 -> 1.16Improved
add LDPO on seed pairs (ablation)DreamFuse · DreamFuse test setVisionReward: 5.28 -> 5.52Improved
add copy-paste negative loss L_LDPO (ablation)DreamFuse w/ LDPO · DreamFuse test setCLIP: 35.36 -> 35.51Improved
add L_noise loss (ablation)DreamFuse w/ LDPO + L_LDPO · DreamFuse test setVisionReward: 5.58 -> 5.56No clear effect
lower text dropout probability p to 80% (ablation)DreamFuse · DreamFuse test setCLIP: p=99% chosen over 80%Hurt
set dilation factor alpha to 0 (copy-paste treated as preferred) (ablation)DreamFuse LDPO · DreamFuse test setVisionReward: alpha 0 gives significant VR decline vs alpha 1.5Hurt
set dilation factor alpha to 1 (only bounding box region) (ablation)DreamFuse LDPO · DreamFuse test setVisionReward: alpha 1 gives a performance drop vs alpha 1.5Hurt
DreamFuse versus second-best method on TF-ICON datasetDreamFuse · TF-ICON datasetVisionReward: 2.37 -> 3.27Improved
DreamFuse versus second-best method on DreamFuse test setDreamFuse · DreamFuse test setVisionReward: 4.14 -> 5.56Improved

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