LoVoRA: Text-guided and Mask-free Video Object Removal and Addition with Learnable Object-aware Localization
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908689989894144 |
|---|---|
| author | Xiao, Zhihan Liu, Lin Gao, Yixin Zhang, Xiaopeng Che, Haoxuan Mai, Songping Tian, Qi |
| author_facet | Xiao, Zhihan Liu, Lin Gao, Yixin Zhang, Xiaopeng Che, Haoxuan Mai, Songping Tian, Qi |
| contents | Text-guided video editing, particularly for object removal and addition, remains a challenging task due to the need for precise spatial and temporal consistency. Existing methods often rely on auxiliary masks or reference images for editing guidance, which limits their scalability and generalization. To address these issues, we propose LoVoRA, a novel framework for mask-free video object removal and addition using object-aware localization mechanism. Our approach utilizes a unique dataset construction pipeline that integrates image-to-video translation, optical flow-based mask propagation, and video inpainting, enabling temporally consistent edits. The core innovation of LoVoRA is its learnable object-aware localization mechanism, which provides dense spatio-temporal supervision for both object insertion and removal tasks. By leveraging a Diffusion Mask Predictor, LoVoRA achieves end-to-end video editing without requiring external control signals during inference. Extensive experiments and human evaluation demonstrate the effectiveness and high-quality performance of LoVoRA. https://cz-5f.github.io/LoVoRA.github.io |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_02933 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LoVoRA: Text-guided and Mask-free Video Object Removal and Addition with Learnable Object-aware Localization Xiao, Zhihan Liu, Lin Gao, Yixin Zhang, Xiaopeng Che, Haoxuan Mai, Songping Tian, Qi Computer Vision and Pattern Recognition Text-guided video editing, particularly for object removal and addition, remains a challenging task due to the need for precise spatial and temporal consistency. Existing methods often rely on auxiliary masks or reference images for editing guidance, which limits their scalability and generalization. To address these issues, we propose LoVoRA, a novel framework for mask-free video object removal and addition using object-aware localization mechanism. Our approach utilizes a unique dataset construction pipeline that integrates image-to-video translation, optical flow-based mask propagation, and video inpainting, enabling temporally consistent edits. The core innovation of LoVoRA is its learnable object-aware localization mechanism, which provides dense spatio-temporal supervision for both object insertion and removal tasks. By leveraging a Diffusion Mask Predictor, LoVoRA achieves end-to-end video editing without requiring external control signals during inference. Extensive experiments and human evaluation demonstrate the effectiveness and high-quality performance of LoVoRA. https://cz-5f.github.io/LoVoRA.github.io |
| title | LoVoRA: Text-guided and Mask-free Video Object Removal and Addition with Learnable Object-aware Localization |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.02933 |