Style-Editor: Text-driven object-centric style editing

Jihun Park, Jongmin Gim, Kyoungmin Lee, Seunghun Lee, Sunghoon Im
8/16/2024
cs.CV

No confident code implementation found for this paper.

Abstract

We present Text-driven object-centric style editing model named Style-Editor, a novel method that guides style editing at an object-centric level using textual inputs. The core of Style-Editor is our Patch-wise Co-Directional (PCD) loss, meticulously designed for precise object-centric editing that are closely aligned with the input text. This loss combines a patch directional loss for text-guided style direction and a patch distribution consistency loss for even CLIP embedding distribution across object regions. It ensures a seamless and harmonious style editing across object regions. Key to our method are the Text-Matched Patch Selection (TMPS) and Pre-fixed Region Selection (PRS) modules for identifying object locations via text, eliminating the need for segmentation masks. Lastly, we introduce an Adaptive Background Preservation (ABP) loss to maintain the original style and structural essence of the image's background. This loss is applied to dynamically identified background areas. Extensive experiments underline the effectiveness of our approach in creating visually coherent and textually aligned style editing.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Style-Editor: Text-driven object-centric style editing

100% match2026

FlexEdit: Flexible and Controllable Diffusion-based Object-centric Image Editing

85% match2024

Local Prompt Adaptation for Style-Consistent Multi-Object Generation in Diffusion Models

82% match2025

Improved 3D Scene Stylization via Text-Guided Generative Image Editing with Region-Based Control

82% match1 repo2025

Neural Scene Designer: Self-Styled Semantic Image Manipulation

82% match2025

StyleBooth: Image Style Editing with Multimodal Instruction

82% match1 repo5492024

Cite this paper

@article{park2024styleeditor,
  title  = {Style-Editor: Text-driven object-centric style editing},
  author = {Jihun Park and Jongmin Gim and Kyoungmin Lee and Seunghun Lee and Sunghoon Im},
  year   = {2024},
  eprint = {2408.08461},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2408.08461v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2408.08461.svg)](https://codeofpaper.com/paper/2408.08461)

Discussion