Track, Inpaint, Resplat: Subject-driven 3D and 4D Generation with Progressive Texture Infilling
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908615051313152 |
|---|---|
| author | Zheng, Shuhong Mirzaei, Ashkan Gilitschenski, Igor |
| author_facet | Zheng, Shuhong Mirzaei, Ashkan Gilitschenski, Igor |
| contents | Current 3D/4D generation methods are usually optimized for photorealism, efficiency, and aesthetics. However, they often fail to preserve the semantic identity of the subject across different viewpoints. Adapting generation methods with one or few images of a specific subject (also known as Personalization or Subject-driven generation) allows generating visual content that align with the identity of the subject. However, personalized 3D/4D generation is still largely underexplored. In this work, we introduce TIRE (Track, Inpaint, REsplat), a novel method for subject-driven 3D/4D generation. It takes an initial 3D asset produced by an existing 3D generative model as input and uses video tracking to identify the regions that need to be modified. Then, we adopt a subject-driven 2D inpainting model for progressively infilling the identified regions. Finally, we resplat the modified 2D multi-view observations back to 3D while still maintaining consistency. Extensive experiments demonstrate that our approach significantly improves identity preservation in 3D/4D generation compared to state-of-the-art methods. Our project website is available at https://zsh2000.github.io/track-inpaint-resplat.github.io/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_23605 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Track, Inpaint, Resplat: Subject-driven 3D and 4D Generation with Progressive Texture Infilling Zheng, Shuhong Mirzaei, Ashkan Gilitschenski, Igor Computer Vision and Pattern Recognition Artificial Intelligence Graphics Machine Learning Robotics Current 3D/4D generation methods are usually optimized for photorealism, efficiency, and aesthetics. However, they often fail to preserve the semantic identity of the subject across different viewpoints. Adapting generation methods with one or few images of a specific subject (also known as Personalization or Subject-driven generation) allows generating visual content that align with the identity of the subject. However, personalized 3D/4D generation is still largely underexplored. In this work, we introduce TIRE (Track, Inpaint, REsplat), a novel method for subject-driven 3D/4D generation. It takes an initial 3D asset produced by an existing 3D generative model as input and uses video tracking to identify the regions that need to be modified. Then, we adopt a subject-driven 2D inpainting model for progressively infilling the identified regions. Finally, we resplat the modified 2D multi-view observations back to 3D while still maintaining consistency. Extensive experiments demonstrate that our approach significantly improves identity preservation in 3D/4D generation compared to state-of-the-art methods. Our project website is available at https://zsh2000.github.io/track-inpaint-resplat.github.io/. |
| title | Track, Inpaint, Resplat: Subject-driven 3D and 4D Generation with Progressive Texture Infilling |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Graphics Machine Learning Robotics |
| url | https://arxiv.org/abs/2510.23605 |