Editing multiple elements of an image in a single forward pass is a practical alternative to multi-turn image manipulation, offering improved efficiency and potentially better harmonization. However, when several instructions target different regions, semantic interference often leads to attribute leakage and poor edit disentanglement, especially as the number of edits increases. In this work, we propose MICE (Multi-Instance Concurrent Editing), a training-free strategy for scalable multi-instance image editing with Multimodal Diffusion Transformers. MICE modifies the additive bias of joint attention to regulate interactions between instance-specific edit instructions, latent, and context tokens identified via user-provided segmentation masks. Specifically, MICE allows intra-instance attention, penalizes interactions between neighboring region tokens, and suppresses unrelated cross-instance attention. As a result, our method enforces attribute binding while preserving global visual consistency. We evaluate MICE on LoMOE-Bench and introduce MICE-Bench, a more challenging benchmark with an average of 8.5 concurrent edits per image. The experiments demonstrate that our approach outperforms strong baselines and recent competitors in terms of visual quality preservation and faithfulness to the editing instructions.

Editing Everything Everywhere All at Once / Quattrini, F., Zaccagnino, C., Simsar, E., Tintoré Gazulla, M., Cucchiara, R., Tonioni, A., Cascianelli, S.. - (2026). (20th European Conference on Computer Vision, ECCV 2026 Malmö, Sweden SEP 8-OCT 12, 2024).

Editing Everything Everywhere All at Once

Fabio Quattrini;Carmine Zaccagnino;Rita Cucchiara;Silvia Cascianelli
2026

Abstract

Editing multiple elements of an image in a single forward pass is a practical alternative to multi-turn image manipulation, offering improved efficiency and potentially better harmonization. However, when several instructions target different regions, semantic interference often leads to attribute leakage and poor edit disentanglement, especially as the number of edits increases. In this work, we propose MICE (Multi-Instance Concurrent Editing), a training-free strategy for scalable multi-instance image editing with Multimodal Diffusion Transformers. MICE modifies the additive bias of joint attention to regulate interactions between instance-specific edit instructions, latent, and context tokens identified via user-provided segmentation masks. Specifically, MICE allows intra-instance attention, penalizes interactions between neighboring region tokens, and suppresses unrelated cross-instance attention. As a result, our method enforces attribute binding while preserving global visual consistency. We evaluate MICE on LoMOE-Bench and introduce MICE-Bench, a more challenging benchmark with an average of 8.5 concurrent edits per image. The experiments demonstrate that our approach outperforms strong baselines and recent competitors in terms of visual quality preservation and faithfulness to the editing instructions.
2026
30-giu-2026
20th European Conference on Computer Vision, ECCV 2026
Malmö, Sweden
SEP 8-OCT 12, 2024
Quattrini, Fabio; Zaccagnino, Carmine; Simsar, Enis; Tintoré Gazulla, Marta; Cucchiara, Rita; Tonioni, Alessio; Cascianelli, Silvia
Editing Everything Everywhere All at Once / Quattrini, F., Zaccagnino, C., Simsar, E., Tintoré Gazulla, M., Cucchiara, R., Tonioni, A., Cascianelli, S.. - (2026). (20th European Conference on Computer Vision, ECCV 2026 Malmö, Sweden SEP 8-OCT 12, 2024).
File in questo prodotto:
Non ci sono file associati a questo prodotto.
Pubblicazioni consigliate

Licenza Creative Commons
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11380/1414448
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
  • OpenAlex ND
social impact