Less Gaussians, Texture More: 4K Feed-Forward Textured Splatting
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908915902447616 |
|---|---|
| author | Lao, Yixing Bai, Xuyang Wu, Xiaoyang Yan, Nuoyuan Luo, Zixin Fang, Tian Nahmias, Jean-Daniel Tsin, Yanghai Li, Shiwei Zhao, Hengshuang |
| author_facet | Lao, Yixing Bai, Xuyang Wu, Xiaoyang Yan, Nuoyuan Luo, Zixin Fang, Tian Nahmias, Jean-Daniel Tsin, Yanghai Li, Shiwei Zhao, Hengshuang |
| contents | Existing feed-forward 3D Gaussian Splatting methods predict pixel-aligned primitives, leading to a quadratic growth in primitive count as resolution increases. This fundamentally limits their scalability, making high-resolution synthesis such as 4K intractable. We introduce LGTM (Less Gaussians, Texture More), a feed-forward framework that overcomes this resolution scaling barrier. By predicting compact Gaussian primitives coupled with per-primitive textures, LGTM decouples geometric complexity from rendering resolution. This approach enables high-fidelity 4K novel view synthesis without per-scene optimization, a capability previously out of reach for feed-forward methods, all while using significantly fewer Gaussian primitives. Project page: https://yxlao.github.io/lgtm/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_25745 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Less Gaussians, Texture More: 4K Feed-Forward Textured Splatting Lao, Yixing Bai, Xuyang Wu, Xiaoyang Yan, Nuoyuan Luo, Zixin Fang, Tian Nahmias, Jean-Daniel Tsin, Yanghai Li, Shiwei Zhao, Hengshuang Computer Vision and Pattern Recognition Existing feed-forward 3D Gaussian Splatting methods predict pixel-aligned primitives, leading to a quadratic growth in primitive count as resolution increases. This fundamentally limits their scalability, making high-resolution synthesis such as 4K intractable. We introduce LGTM (Less Gaussians, Texture More), a feed-forward framework that overcomes this resolution scaling barrier. By predicting compact Gaussian primitives coupled with per-primitive textures, LGTM decouples geometric complexity from rendering resolution. This approach enables high-fidelity 4K novel view synthesis without per-scene optimization, a capability previously out of reach for feed-forward methods, all while using significantly fewer Gaussian primitives. Project page: https://yxlao.github.io/lgtm/ |
| title | Less Gaussians, Texture More: 4K Feed-Forward Textured Splatting |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.25745 |