paper-with-me

홈 › Papers

DuET: Dual Expert Trajectories for Diffusion Image Editing

2026-06-11 · Lidia Troeshestova, Alexander Ustyuzhanin, Sergey Kastryulin arxiv

Recent diffusion editors perform diverse instruction-based edits while conditioning on the source image at every denoising step. Yet persistent source-image conditioning can limit how fully an edit is executed and how natural the result appears, especially when the target scene diverges substantially from the input. We introduce DuET (Dual Expert Trajectories), a training-free inference method that temporarily relaxes source-image conditioning by transitioning through a text-to-image phase before returning to edit mode, allowing the denoising trajectory to move toward the target distribution while retaining the structural benefits of image-conditioned editing. Without modifying model weights or increasing sampling cost, DuET consistently improves instruction relevance, semantic fidelity, and perceptual quality across diverse models and benchmarks. In some cases, these gains come with a modest reduction in source-image preservation, revealing a predictable trade-off between source preservation and edit fidelity.

📄 PDF Abstract BibTeX arXiv:2606.13303

Code (0)

등록된 구현이 없습니다.

Tasks

Image Editing

Similar Papers 제목 키워드 기반

DUET: Dual-Paradigm Adaptive Expert Triage with Single-cell Inductive Prior for Spatial Transcriptomics Prediction

2026-05-13 · Junchao Zhu, Ruining Deng, Junlin Guo, Tianyuan Yao 외 arxiv

Inferring spatially resolved gene expression from histology images offers a cost-effective complement to spatial transcriptomics (ST). However, existing methods reduce this task to a simple morphology-to-expression mappi…

MeDUET: Disentangled Unified Pretraining for 3D Medical Image Synthesis and Analysis

2026-02-19 · Junkai Liu, Ling Shao, Le Zhang arxiv

Self-supervised learning (SSL) and diffusion models have respectively advanced representation learning and generative modeling for high-dimensional 3D visual data, yet they are often developed as separate paradigms. Thei…

Self-Supervised LearningRepresentation LearningDomain Generalization

Zero-Shot Duet Singing Voices Separation with Diffusion Models

2023-11-13 · Chin-Yun Yu, Emilian Postolache, Emanuele Rodolà, György Fazekas

In recent studies, diffusion models have shown promise as priors for solving audio inverse problems. These models allow us to sample from the posterior distribution of a target signal given an observed signal by manipula…

DuetFair: Coupling Inter- and Intra-Subgroup Robustness for Fair Medical Image Segmentation

2026-05-11 · Yiqi Tian, Sangjoon Park, Bo Zeng, Pengfei Jin 외 arxiv

Medical image segmentation models can perform unevenly across subgroups. Most existing fairness methods focus on improving average subgroup performance, implicitly treating each subgroup as internally homogeneous. Howeve…

Medical Image Segmentation

Duet: Dual-Robot Understanding via Efficient Teaching

2026-06-18 · Yiqi Zhao, Ruohai Ge, Celina Shiyu Wang, Junjie Ye 외 arxiv

Dual-robot collaboration enables tasks that exceed the reach and payload of a single robot, such as collaboratively transporting objects across environments and executing coordinated handovers. Data acquisition is the pr…