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.

翻译：为实现像素级图像操控，以点或轨迹为条件的拖拽式图像编辑方法正受到广泛关注。现有方法大多遵循“移动-跟踪”框架，其中跟踪丢失与跟踪模糊是难以避免的挑战性问题。其他框架下的方法则存在源图像与目标编辑图像差异过大、中间点设置不合理导致编辑成功率低等各类缺陷。为规避这些问题，我们提出了首个基于“预测-移动”框架的拖拽式编辑方法DynaDrag。该方法通过迭代执行运动预测与运动监督模块实现编辑：在每轮迭代中，运动预测模块首先预测手柄点应移动的目标位置，随后运动监督模块据此执行拖拽操作。我们还提出动态调整有效手柄点的策略以进一步提升性能。在面部及人体数据集上的实验验证了本方法相较于现有工作的优越性。