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

TL;DR

Style-Editor is a novel text-driven, object-centric style editing method that uses a new loss function and modules to precisely modify object styles based on textual input without needing segmentation masks.

Contribution

The paper introduces Style-Editor, a new approach for object-centric style editing guided by text, featuring the PCD loss, TMPS, PRS, and ABP loss for improved accuracy and coherence.

Findings

Effective text-guided style editing demonstrated through extensive experiments.

Achieves precise object-centric modifications aligned with textual descriptions.

Maintains background style and structure while editing objects.

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.