Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2511.15197 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914507241029632 |
|---|---|
| author | Chittersu, Raghu Vamsi Rathore, Yuvraj Singh Adlinge, Pranav Swami, Kunal |
| author_facet | Chittersu, Raghu Vamsi Rathore, Yuvraj Singh Adlinge, Pranav Swami, Kunal |
| contents | Reference-based object composition involves integrating foreground reference image with background scene to produce harmonious fused image. This task becomes particularly challenging in cross-domain scenarios, where models must balance preserving the reference object's identity while harmonizing them to match stylized environments. This under-explored problem is currently split between practical "blenders" that lack generative fidelity and "generators" that require impractical, per-subject online finetuning. In this work, we introduce Insert In Style, the first zero-shot generative framework that is both practical and high-fidelity. Our core contribution is a unified framework with two key innovations: (i) a novel multi-stage training protocol that disentangles representations for identity, style, and composition, and (ii) a specialized masked-attention architecture that surgically enforces this disentanglement during generation (iii) A prior preservation objective that keeps learned identity and style priors intact. By design, this approach mitigates concept interference typical in unified-attention architectures while ensuring robust generalization across diverse references and styles. Our framework is trained on a new 115k sample dataset, curated from a novel data pipeline. This pipeline couples large-scale generation with a rigorous, iterative human-in-the-loop filtering process to ensure both high-fidelity semantic identity and style coherence. Unlike prior work, our model is truly zero-shot and requires no text prompts. We also introduce a new public benchmark for stylized composition. We demonstrate state-of-the-art performance, significantly outperforming existing methods on both identity and style metrics, a result strongly corroborated by user studies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_15197 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Insert In Style: A Zero-Shot Generative Framework for Harmonious Cross-Domain Object Composition Chittersu, Raghu Vamsi Rathore, Yuvraj Singh Adlinge, Pranav Swami, Kunal Computer Vision and Pattern Recognition Reference-based object composition involves integrating foreground reference image with background scene to produce harmonious fused image. This task becomes particularly challenging in cross-domain scenarios, where models must balance preserving the reference object's identity while harmonizing them to match stylized environments. This under-explored problem is currently split between practical "blenders" that lack generative fidelity and "generators" that require impractical, per-subject online finetuning. In this work, we introduce Insert In Style, the first zero-shot generative framework that is both practical and high-fidelity. Our core contribution is a unified framework with two key innovations: (i) a novel multi-stage training protocol that disentangles representations for identity, style, and composition, and (ii) a specialized masked-attention architecture that surgically enforces this disentanglement during generation (iii) A prior preservation objective that keeps learned identity and style priors intact. By design, this approach mitigates concept interference typical in unified-attention architectures while ensuring robust generalization across diverse references and styles. Our framework is trained on a new 115k sample dataset, curated from a novel data pipeline. This pipeline couples large-scale generation with a rigorous, iterative human-in-the-loop filtering process to ensure both high-fidelity semantic identity and style coherence. Unlike prior work, our model is truly zero-shot and requires no text prompts. We also introduce a new public benchmark for stylized composition. We demonstrate state-of-the-art performance, significantly outperforming existing methods on both identity and style metrics, a result strongly corroborated by user studies. |
| title | Insert In Style: A Zero-Shot Generative Framework for Harmonious Cross-Domain Object Composition |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.15197 |