DynaDrag: 通过运动预测实现动态拖拽式图像编辑
DynaDrag: Dynamic Drag-Style Image Editing by Motion Prediction
AI总结：
DynaDrag通过运动预测和动态调整手柄点，实现了更高效的拖拽式图像编辑方法，优于现有技术。
摘要：
为了实现像素级图像编辑，利用点或轨迹作为条件进行图像编辑的拖拽式图像编辑方法正受到广泛关注。大多数先前方法遵循移动和跟踪框架，在此框架中，丢失跟踪和模糊跟踪是不可避免的挑战性问题。其他方法在不同框架下则面临各种问题，例如源图像与目标编辑图像之间的巨大差距以及不合理的中间点，这可能导致编辑性低。为了避免这些问题，我们提出了DynaDrag，这是首个基于预测和移动框架的拖拽方法。在DynaDrag中，运动预测和运动监督是迭代进行的。在每次迭代中，运动预测首先预测手柄点应移动到何处，然后运动监督相应地拖动它们。我们还提出动态调整有效手柄点以进一步提高性能。在人脸和人体数据集上的实验展示了其优于先前方法的优越性。
英文摘要：
To achieve pixel-level image manipulation, drag-style image editing which edits images using points or trajectories as conditions is attracting widespread attention. Most previous methods follow move-and-track framework, in which miss tracking and ambiguous tracking are unavoidable challenging issues. Other methods under different frameworks suffer from various problems like the huge gap between source image and target edited image as well as unreasonable intermediate point which can lead to low editability. To avoid these problems, we propose DynaDrag, the first dragging method under predict-and-move framework. In DynaDrag, Motion Prediction and Motion Supervision are performed iteratively. In each iteration, Motion Prediction first predicts where the handle points should move, and then Motion Supervision drags them accordingly. We also propose to dynamically adjust the valid handle points to further improve the performance. Experiments on face and human datasets showcase the superiority over previous works.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
