English

Less Gaussians, Texture More: 4K Feed-Forward Textured Splatting

Computer Vision and Pattern Recognition 2026-03-27 v1

Abstract

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/

Keywords

Cite

@article{arxiv.2603.25745,
  title  = {Less Gaussians, Texture More: 4K Feed-Forward Textured Splatting},
  author = {Yixing Lao and Xuyang Bai and Xiaoyang Wu and Nuoyuan Yan and Zixin Luo and Tian Fang and Jean-Daniel Nahmias and Yanghai Tsin and Shiwei Li and Hengshuang Zhao},
  journal= {arXiv preprint arXiv:2603.25745},
  year   = {2026}
}
R2 v1 2026-07-01T11:39:42.246Z