HumanSplat: Generalizable Single-Image Human Gaussian Splatting with Structure Priors
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913567599493120 |
|---|---|
| author | Pan, Panwang Su, Zhuo Lin, Chenguo Fan, Zhen Zhang, Yongjie Li, Zeming Shen, Tingting Mu, Yadong Liu, Yebin |
| author_facet | Pan, Panwang Su, Zhuo Lin, Chenguo Fan, Zhen Zhang, Yongjie Li, Zeming Shen, Tingting Mu, Yadong Liu, Yebin |
| contents | Despite recent advancements in high-fidelity human reconstruction techniques, the requirements for densely captured images or time-consuming per-instance optimization significantly hinder their applications in broader scenarios. To tackle these issues, we present HumanSplat which predicts the 3D Gaussian Splatting properties of any human from a single input image in a generalizable manner. In particular, HumanSplat comprises a 2D multi-view diffusion model and a latent reconstruction transformer with human structure priors that adeptly integrate geometric priors and semantic features within a unified framework. A hierarchical loss that incorporates human semantic information is further designed to achieve high-fidelity texture modeling and better constrain the estimated multiple views. Comprehensive experiments on standard benchmarks and in-the-wild images demonstrate that HumanSplat surpasses existing state-of-the-art methods in achieving photorealistic novel-view synthesis. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_12459 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | HumanSplat: Generalizable Single-Image Human Gaussian Splatting with Structure Priors Pan, Panwang Su, Zhuo Lin, Chenguo Fan, Zhen Zhang, Yongjie Li, Zeming Shen, Tingting Mu, Yadong Liu, Yebin Computer Vision and Pattern Recognition Despite recent advancements in high-fidelity human reconstruction techniques, the requirements for densely captured images or time-consuming per-instance optimization significantly hinder their applications in broader scenarios. To tackle these issues, we present HumanSplat which predicts the 3D Gaussian Splatting properties of any human from a single input image in a generalizable manner. In particular, HumanSplat comprises a 2D multi-view diffusion model and a latent reconstruction transformer with human structure priors that adeptly integrate geometric priors and semantic features within a unified framework. A hierarchical loss that incorporates human semantic information is further designed to achieve high-fidelity texture modeling and better constrain the estimated multiple views. Comprehensive experiments on standard benchmarks and in-the-wild images demonstrate that HumanSplat surpasses existing state-of-the-art methods in achieving photorealistic novel-view synthesis. |
| title | HumanSplat: Generalizable Single-Image Human Gaussian Splatting with Structure Priors |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2406.12459 |