ObjectMover: Generative Object Movement with Video Prior
Xin Yu, Tianyu Wang, Soo Ye Kim, Paul Guerrero, Xi Chen, Qing Liu, Zhe Lin, Xiaojuan Qi
2025-03-12
Summary
This paper talks about ObjectMover, an AI tool that moves objects in images realistically by using knowledge from video-generation models to fix lighting, shadows, and missing areas.
What's the problem?
Moving objects in photos looks simple but is tricky because lighting, shadows, and empty spaces need to match the new spot perfectly, and existing tools struggle with complex scenes.
What's the solution?
ObjectMover uses a video-generation AI retrained to handle single images, creates fake training data using game engines, and learns from both fake and real videos to improve its skills.
Why it matters?
This helps photo editors and designers move objects in images more realistically, saving time and making edits look natural without manual fixes.
Abstract
Simple as it seems, moving an object to another location within an image is, in fact, a challenging image-editing task that requires re-harmonizing the lighting, adjusting the pose based on perspective, accurately filling occluded regions, and ensuring coherent synchronization of shadows and reflections while maintaining the object identity. In this paper, we present ObjectMover, a generative model that can perform object movement in highly challenging scenes. Our key insight is that we model this task as a sequence-to-sequence problem and fine-tune a video generation model to leverage its knowledge of consistent object generation across video frames. We show that with this approach, our model is able to adjust to complex real-world scenarios, handling extreme lighting harmonization and object effect movement. As large-scale data for object movement are unavailable, we construct a data generation pipeline using a modern game engine to synthesize high-quality data pairs. We further propose a multi-task learning strategy that enables training on real-world video data to improve the model generalization. Through extensive experiments, we demonstrate that ObjectMover achieves outstanding results and adapts well to real-world scenarios.