2024/03/07 by Yutao Cui, Cui, Yutao, Xiaotong Zhao +9 · 6 citations
Computer Science · Engineering · #Advanced Image and Video Retrieval Techniques #Computer Graphics and Visualization Techniques #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Robotics and Sensor-Based Localization
paper · pdf · doi:10.48550/arxiv.2403.04437
openalex publication_date 2024/03/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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.