Mover360: Controllable Object Manipulation in 360° Panoramic Images
- Published
- Source
- arXiv
- Paper number
- 1004
- Field
- Computer Vision
- arXiv ID
- 2608.23238
Key points
- It focuses on moving objects in 360-degree images while also handling deletion and insertion in a single model.
- A single point click lets it infer size, support, and lighting, while boxes and masks also allow precise control.
- A UE5 pipeline produced 12,150 training pairs (60,750 pairs per epoch) and a 210+50 benchmark.
- Across both synthetic and real domains, it outperformed leading perspective-image editing, insertion, and inpainting methods in both reconstruction fidelity and semantic consistency.
- However, instructions are fixed to three operations, so it does not yet support edits that change object attributes or specify complex relationships in words.
Paper links
External research summaries. These are not HDATF publications or measured product results.