Research
STEPS: Scene Text Editing with Preserved Style Using Diffusion and Contrastive Style Encoding
arXiv:2609.38636v1 Announce Type: new Abstract: We introduce Scene Text Editing with Preserved Style (STEPS), a novel diffusion model architecture for quality text replacement in images. Scene Text Ed
arXiv:2609.38636v1 Announce Type: new Abstract: We introduce Scene Text Editing with Preserved Style (STEPS), a novel diffusion model architecture for quality text replacement in images. Scene Text Editing (STE), also known as Visual Text Editing, consists of changing the textual content in an image while conserving the original style, e.g. font, colors, orientation, background, etc. STEPS advances the state of the art in STE through directed focus on improved style preservation. We introduce a style encoder for visual text that captures style independently of textual content, and a model architecture that combines the style encoder with multiple semantic conditions (target text characters encoding and rendered glyphs). STEPS achieves superior results to previous STE methods in style preservation, output readability, and subjective quality.
Related
- Self-Prompting Diffusion Transformer for Open-Vocabulary Scene Text Editing via In-Context Learning
- InnoText: A Unified Model for Visual Text Generation and Editing
- Refinement Is Inherently Editable: Training-Free Prompt-to-Prompt Image Editing with Generative Refinement Network
- MegaStyle: Constructing Diverse and Scalable Style Dataset via Consistent Text-to-Image Style Mapping
Source: arXiv cs.CV | 2026-10-01