StableDrag: Stable Dragging for Point-based Image Editing

TL;DR

StableDrag introduces a novel framework for point-based image editing that enhances stability and accuracy in dragging operations by employing discriminative point tracking and confidence-based latent enhancement, outperforming previous methods.

Contribution

The paper proposes a stable and precise drag-based editing framework with new point tracking and motion supervision strategies, improving long-range manipulation stability and latent quality.

Findings

Enhanced stability in long-range image manipulation

Superior performance on DragBench benchmark

Effective in both GAN and diffusion models

Abstract

Point-based image editing has attracted remarkable attention since the emergence of DragGAN. Recently, DragDiffusion further pushes forward the generative quality via adapting this dragging technique to diffusion models. Despite these great success, this dragging scheme exhibits two major drawbacks, namely inaccurate point tracking and incomplete motion supervision, which may result in unsatisfactory dragging outcomes. To tackle these issues, we build a stable and precise drag-based editing framework, coined as StableDrag, by designing a discirminative point tracking method and a confidence-based latent enhancement strategy for motion supervision. The former allows us to precisely locate the updated handle points, thereby boosting the stability of long-range manipulation, while the latter is responsible for guaranteeing the optimized latent as high-quality as possible across all the manipulation steps. Thanks to these unique designs, we instantiate two types of image editing models including StableDrag-GAN and StableDrag-Diff, which attains more stable dragging performance, through extensive qualitative experiments and quantitative assessment on DragBench.