Summary
LGTM (Less Gaussians, Texture More) is a feed-forward framework for 3D Gaussian Splatting that overcomes the resolution scaling barrier of existing methods. Current feed-forward approaches predict pixel-aligned primitives, causing primitive count to grow quadratically with resolution and making 4K synthesis intractable. LGTM instead predicts compact Gaussian primitives coupled with per-primitive textures, decoupling geometric complexity from rendering resolution. This enables high-fidelity 4K novel view synthesis without per-scene optimization — previously out of reach for feed-forward methods — while using significantly fewer Gaussian primitives. Paper by Yixing Lao, Xuyang Bai, Xiaoyang Wu, and colleagues, published on arXiv as 2603.25745 with project page at yxlao.github.io/lgtm/.
Overview
- Field: Computer Vision
- arXiv: 2603.25745
- Project page: https://yxlao.github.io/lgtm/
- Authors: Yixing Lao, Xuyang Bai, Xiaoyang Wu, Nuoyuan Yan, Zixin Luo, Tian Fang, Jean-Daniel Nahmias, Yanghai Tsin, Shiwei Li, Hengshuang Zhao
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.
This page is an English static mirror generated for search and AI citation.
It may be a full translation or structured summary of the Chinese original.
Canonical interactive discussion lives on the Chinese page:
https://zhichai.net/topic/177169362