ReStyle3D: Scene-Level Appearance Transfer with Semantic Correspondences
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916707784720384 |
|---|---|
| author | Zhu, Liyuan Cai, Shengqu Huang, Shengyu Wetzstein, Gordon Khosravan, Naji Armeni, Iro |
| author_facet | Zhu, Liyuan Cai, Shengqu Huang, Shengyu Wetzstein, Gordon Khosravan, Naji Armeni, Iro |
| contents | We introduce ReStyle3D, a novel framework for scene-level appearance transfer from a single style image to a real-world scene represented by multiple views. The method combines explicit semantic correspondences with multi-view consistency to achieve precise and coherent stylization. Unlike conventional stylization methods that apply a reference style globally, ReStyle3D uses open-vocabulary segmentation to establish dense, instance-level correspondences between the style and real-world images. This ensures that each object is stylized with semantically matched textures. It first transfers the style to a single view using a training-free semantic-attention mechanism in a diffusion model. It then lifts the stylization to additional views via a learned warp-and-refine network guided by monocular depth and pixel-wise correspondences. Experiments show that ReStyle3D consistently outperforms prior methods in structure preservation, perceptual style similarity, and multi-view coherence. User studies further validate its ability to produce photo-realistic, semantically faithful results. Our code, pretrained models, and dataset will be publicly released, to support new applications in interior design, virtual staging, and 3D-consistent stylization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_10377 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ReStyle3D: Scene-Level Appearance Transfer with Semantic Correspondences Zhu, Liyuan Cai, Shengqu Huang, Shengyu Wetzstein, Gordon Khosravan, Naji Armeni, Iro Computer Vision and Pattern Recognition Graphics We introduce ReStyle3D, a novel framework for scene-level appearance transfer from a single style image to a real-world scene represented by multiple views. The method combines explicit semantic correspondences with multi-view consistency to achieve precise and coherent stylization. Unlike conventional stylization methods that apply a reference style globally, ReStyle3D uses open-vocabulary segmentation to establish dense, instance-level correspondences between the style and real-world images. This ensures that each object is stylized with semantically matched textures. It first transfers the style to a single view using a training-free semantic-attention mechanism in a diffusion model. It then lifts the stylization to additional views via a learned warp-and-refine network guided by monocular depth and pixel-wise correspondences. Experiments show that ReStyle3D consistently outperforms prior methods in structure preservation, perceptual style similarity, and multi-view coherence. User studies further validate its ability to produce photo-realistic, semantically faithful results. Our code, pretrained models, and dataset will be publicly released, to support new applications in interior design, virtual staging, and 3D-consistent stylization. |
| title | ReStyle3D: Scene-Level Appearance Transfer with Semantic Correspondences |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2502.10377 |