Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2512.17573 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908722554470400 |
|---|---|
| author | Wang, Qilong Ming, Xiaofan Lin, Zhenyi Li, Jinwen Ren, Dongwei Zuo, Wangmeng Hu, Qinghua |
| author_facet | Wang, Qilong Ming, Xiaofan Lin, Zhenyi Li, Jinwen Ren, Dongwei Zuo, Wangmeng Hu, Qinghua |
| contents | Virtual furniture synthesis, which seamlessly integrates reference objects into indoor scenes while maintaining geometric coherence and visual realism, holds substantial promise for home design and e-commerce applications. However, this field remains underexplored due to the scarcity of reproducible benchmarks and the limitations of existing image composition methods in achieving high-fidelity furniture synthesis while preserving background integrity. To overcome these challenges, we first present RoomBench++, a comprehensive and publicly available benchmark dataset tailored for this task. It consists of 112,851 training pairs and 1,832 testing pairs drawn from both real-world indoor videos and realistic home design renderings, thereby supporting robust training and evaluation under practical conditions. Then, we propose RoomEditor++, a versatile diffusion-based architecture featuring a parameter-sharing dual diffusion backbone, which is compatible with both U-Net and DiT architectures. This design unifies the feature extraction and inpainting processes for reference and background images. Our in-depth analysis reveals that the parameter-sharing mechanism enforces aligned feature representations, facilitating precise geometric transformations, texture preservation, and seamless integration. Extensive experiments validate that RoomEditor++ is superior over state-of-the-art approaches in terms of quantitative metrics, qualitative assessments, and human preference studies, while highlighting its strong generalization to unseen indoor scenes and general scenes without task-specific fine-tuning. The dataset and source code are available at \url{https://github.com/stonecutter-21/roomeditor}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_17573 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RoomEditor++: A Parameter-Sharing Diffusion Architecture for High-Fidelity Furniture Synthesis Wang, Qilong Ming, Xiaofan Lin, Zhenyi Li, Jinwen Ren, Dongwei Zuo, Wangmeng Hu, Qinghua Computer Vision and Pattern Recognition Virtual furniture synthesis, which seamlessly integrates reference objects into indoor scenes while maintaining geometric coherence and visual realism, holds substantial promise for home design and e-commerce applications. However, this field remains underexplored due to the scarcity of reproducible benchmarks and the limitations of existing image composition methods in achieving high-fidelity furniture synthesis while preserving background integrity. To overcome these challenges, we first present RoomBench++, a comprehensive and publicly available benchmark dataset tailored for this task. It consists of 112,851 training pairs and 1,832 testing pairs drawn from both real-world indoor videos and realistic home design renderings, thereby supporting robust training and evaluation under practical conditions. Then, we propose RoomEditor++, a versatile diffusion-based architecture featuring a parameter-sharing dual diffusion backbone, which is compatible with both U-Net and DiT architectures. This design unifies the feature extraction and inpainting processes for reference and background images. Our in-depth analysis reveals that the parameter-sharing mechanism enforces aligned feature representations, facilitating precise geometric transformations, texture preservation, and seamless integration. Extensive experiments validate that RoomEditor++ is superior over state-of-the-art approaches in terms of quantitative metrics, qualitative assessments, and human preference studies, while highlighting its strong generalization to unseen indoor scenes and general scenes without task-specific fine-tuning. The dataset and source code are available at \url{https://github.com/stonecutter-21/roomeditor}. |
| title | RoomEditor++: A Parameter-Sharing Diffusion Architecture for High-Fidelity Furniture Synthesis |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.17573 |