StyleSplat: 3D Object Style Transfer with Gaussian Splatting
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909252353785856 |
|---|---|
| author | Jain, Sahil Kuthiala, Avik Sethi, Prabhdeep Singh Saxena, Prakanshul |
| author_facet | Jain, Sahil Kuthiala, Avik Sethi, Prabhdeep Singh Saxena, Prakanshul |
| contents | Recent advancements in radiance fields have opened new avenues for creating high-quality 3D assets and scenes. Style transfer can enhance these 3D assets with diverse artistic styles, transforming creative expression. However, existing techniques are often slow or unable to localize style transfer to specific objects. We introduce StyleSplat, a lightweight method for stylizing 3D objects in scenes represented by 3D Gaussians from reference style images. Our approach first learns a photorealistic representation of the scene using 3D Gaussian splatting while jointly segmenting individual 3D objects. We then use a nearest-neighbor feature matching loss to finetune the Gaussians of the selected objects, aligning their spherical harmonic coefficients with the style image to ensure consistency and visual appeal. StyleSplat allows for quick, customizable style transfer and localized stylization of multiple objects within a scene, each with a different style. We demonstrate its effectiveness across various 3D scenes and styles, showcasing enhanced control and customization in 3D creation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_09473 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | StyleSplat: 3D Object Style Transfer with Gaussian Splatting Jain, Sahil Kuthiala, Avik Sethi, Prabhdeep Singh Saxena, Prakanshul Computer Vision and Pattern Recognition Recent advancements in radiance fields have opened new avenues for creating high-quality 3D assets and scenes. Style transfer can enhance these 3D assets with diverse artistic styles, transforming creative expression. However, existing techniques are often slow or unable to localize style transfer to specific objects. We introduce StyleSplat, a lightweight method for stylizing 3D objects in scenes represented by 3D Gaussians from reference style images. Our approach first learns a photorealistic representation of the scene using 3D Gaussian splatting while jointly segmenting individual 3D objects. We then use a nearest-neighbor feature matching loss to finetune the Gaussians of the selected objects, aligning their spherical harmonic coefficients with the style image to ensure consistency and visual appeal. StyleSplat allows for quick, customizable style transfer and localized stylization of multiple objects within a scene, each with a different style. We demonstrate its effectiveness across various 3D scenes and styles, showcasing enhanced control and customization in 3D creation. |
| title | StyleSplat: 3D Object Style Transfer with Gaussian Splatting |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.09473 |