CrimEdit: Controllable Editing for Counterfactual Object Removal, Insertion, and Movement
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918149866127360 |
|---|---|
| author | Jeon, Boseong Lee, Junghyuk Park, Jimin Kim, Kwanyoung Jung, Jingi Lee, Sangwon Shim, Hyunbo |
| author_facet | Jeon, Boseong Lee, Junghyuk Park, Jimin Kim, Kwanyoung Jung, Jingi Lee, Sangwon Shim, Hyunbo |
| contents | Recent works on object removal and insertion have enhanced their performance by handling object effects such as shadows and reflections, using diffusion models trained on counterfactual datasets. However, the performance impact of applying classifier-free guidance to handle object effects across removal and insertion tasks within a unified model remains largely unexplored. To address this gap and improve efficiency in composite editing, we propose CrimEdit, which jointly trains the task embeddings for removal and insertion within a single model and leverages them in a classifier-free guidance scheme -- enhancing the removal of both objects and their effects, and enabling controllable synthesis of object effects during insertion. CrimEdit also extends these two task prompts to be applied to spatially distinct regions, enabling object movement (repositioning) within a single denoising step. By employing both guidance techniques, extensive experiments show that CrimEdit achieves superior object removal, controllable effect insertion, and efficient object movement without requiring additional training or separate removal and insertion stages. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_23708 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CrimEdit: Controllable Editing for Counterfactual Object Removal, Insertion, and Movement Jeon, Boseong Lee, Junghyuk Park, Jimin Kim, Kwanyoung Jung, Jingi Lee, Sangwon Shim, Hyunbo Computer Vision and Pattern Recognition Artificial Intelligence Recent works on object removal and insertion have enhanced their performance by handling object effects such as shadows and reflections, using diffusion models trained on counterfactual datasets. However, the performance impact of applying classifier-free guidance to handle object effects across removal and insertion tasks within a unified model remains largely unexplored. To address this gap and improve efficiency in composite editing, we propose CrimEdit, which jointly trains the task embeddings for removal and insertion within a single model and leverages them in a classifier-free guidance scheme -- enhancing the removal of both objects and their effects, and enabling controllable synthesis of object effects during insertion. CrimEdit also extends these two task prompts to be applied to spatially distinct regions, enabling object movement (repositioning) within a single denoising step. By employing both guidance techniques, extensive experiments show that CrimEdit achieves superior object removal, controllable effect insertion, and efficient object movement without requiring additional training or separate removal and insertion stages. |
| title | CrimEdit: Controllable Editing for Counterfactual Object Removal, Insertion, and Movement |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2509.23708 |