DAV-GSWT: Diffusion-Active-View Sampling for Data-Efficient Gaussian Splatting Wang Tiles
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915935786369024 |
|---|---|
| author | Fu, Rong Wu, Jiekai Wei, Haiyun Jia, Yee Tan Li, Yang Ma, Xiaowen Wu, Wangyu Fong, Simon |
| author_facet | Fu, Rong Wu, Jiekai Wei, Haiyun Jia, Yee Tan Li, Yang Ma, Xiaowen Wu, Wangyu Fong, Simon |
| contents | The emergence of 3D Gaussian Splatting has fundamentally redefined the capabilities of photorealistic neural rendering by enabling high-throughput synthesis of complex environments. While procedural methods like Wang Tiles have recently been integrated to facilitate the generation of expansive landscapes, these systems typically remain constrained by a reliance on densely sampled exemplar reconstructions. We present DAV-GSWT, a data-efficient framework that leverages diffusion priors and active view sampling to synthesize high-fidelity Gaussian Splatting Wang Tiles from minimal input observations. By integrating a hierarchical uncertainty quantification mechanism with generative diffusion models, our approach autonomously identifies the most informative viewpoints while hallucinating missing structural details to ensure seamless tile transitions. Experimental results indicate that our system significantly reduces the required data volume while maintaining the visual integrity and interactive performance necessary for large-scale virtual environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_15355 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DAV-GSWT: Diffusion-Active-View Sampling for Data-Efficient Gaussian Splatting Wang Tiles Fu, Rong Wu, Jiekai Wei, Haiyun Jia, Yee Tan Li, Yang Ma, Xiaowen Wu, Wangyu Fong, Simon Computer Vision and Pattern Recognition The emergence of 3D Gaussian Splatting has fundamentally redefined the capabilities of photorealistic neural rendering by enabling high-throughput synthesis of complex environments. While procedural methods like Wang Tiles have recently been integrated to facilitate the generation of expansive landscapes, these systems typically remain constrained by a reliance on densely sampled exemplar reconstructions. We present DAV-GSWT, a data-efficient framework that leverages diffusion priors and active view sampling to synthesize high-fidelity Gaussian Splatting Wang Tiles from minimal input observations. By integrating a hierarchical uncertainty quantification mechanism with generative diffusion models, our approach autonomously identifies the most informative viewpoints while hallucinating missing structural details to ensure seamless tile transitions. Experimental results indicate that our system significantly reduces the required data volume while maintaining the visual integrity and interactive performance necessary for large-scale virtual environments. |
| title | DAV-GSWT: Diffusion-Active-View Sampling for Data-Efficient Gaussian Splatting Wang Tiles |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.15355 |