paper-with-me

홈 › Papers

VeloEdit: Training-Free Consistent and Continuous Instruction-Based Image Editing via Velocity Field Decomposition

2026-03-11 · Zongqing Li, Zhihui Liu, Yujie Xie, Shansiyuan Wu, Hongshen Lv, Songzhi Su arxiv

Instruction-based image editing aims to modify source content according to textual instructions. However, existing methods built upon flow matching often struggle to maintain consistency in non-edited regions due to denoising-induced reconstruction errors that cause drift in preserved content. Moreover, they typically lack fine-grained control over edit strength. To address these limitations, we propose VeloEdit, a training-free method that enables highly consistent and continuously controllable editing. VeloEdit dynamically identifies editing regions by quantifying the discrepancy between the velocity fields responsible for preserving source content and those driving the desired edits. Based on this partition, we enforce consistency in preservation regions by substituting the editing velocity with the source-restoring velocity, while enabling continuous modulation of edit intensity in target regions via velocity interpolation. Unlike prior works that rely on complex attention manipulation or auxiliary trainable modules, VeloEdit operates directly on the velocity fields. Extensive experiments on Flux.1 Kontext and Qwen-Image-Edit demonstrate that VeloEdit improves visual consistency and editing continuity with negligible additional computational cost. Code is available at https://github.com/xmulzq/VeloEdit.

📄 PDF Abstract BibTeX arXiv:2603.13388

Code (0)

등록된 구현이 없습니다.

Tasks

Image Editing

Similar Papers 제목 키워드 기반

GC-VLN: Instruction as Graph Constraints for Training-free Vision-and-Language Navigation

2025-09-12 · Hang Yin, Haoyu Wei, Xiuwei Xu, Wenxuan Guo 외 arxiv

In this paper, we propose a training-free framework for vision-and-language navigation (VLN). Existing zero-shot VLN methods are mainly designed for discrete environments or involve unsupervised training in continuous si…

MLANet: Multi-Level Attention Network with Sub-instruction for Continuous Vision-and-Language Navigation

2023-03-02 · Zongtao He, Liuyi Wang, Shu Li, Qingqing Yan 외

Vision-and-Language Navigation (VLN) aims to develop intelligent agents to navigate in unseen environments only through language and vision supervision. In the recently proposed continuous settings (continuous VLN), the …

NavigateVision and Language Navigation

Mosaic-IT: Free Compositional Data Augmentation Improves Instruction Tuning

2024-05-22 · Ming Li, Pei Chen, Chenguang Wang, Hongyu Zhao 외

Finetuning large language models with a variety of instruction-response pairs has enhanced their capability to understand and follow instructions. Current instruction tuning primarily relies on teacher models or human in…

Data AugmentationDiversityInstruction Following

Ming-UniAudio: Speech LLM for Joint Understanding, Generation and Editing with Unified Representation

2025-10-26 · Canxiang Yan, Chunxiang Jin, Dawei Huang, Haibing Yu 외 arxiv

Existing speech models suffer from competing requirements on token representations by understanding and generation tasks. This discrepancy in representation prevents speech language models from performing instruction-bas…

ELIQ: A Label-Free Framework for Quality Assessment of Evolving AI-Generated Images

2026-02-03 · Xinyue Li, Zhiming Xu, Min Tang, Zhaolin Cai 외 arxiv

Generative text-to-image models are advancing at an unprecedented pace, continuously shifting the perceptual quality ceiling and rendering previously collected labels unreliable for newer generations. To address this, we…