Less Gaussians, Texture More: 4K Feed-Forward Textured Splatting
This addresses the problem of intractable high-resolution synthesis for feed-forward 3D reconstruction methods, representing a novel advancement rather than an incremental improvement.
The paper tackles the scalability limitation of feed-forward 3D Gaussian Splatting methods, which suffer from quadratic growth in primitive count with resolution, by introducing LGTM, a framework that uses compact Gaussian primitives with per-primitive textures to enable high-fidelity 4K novel view synthesis without per-scene optimization.
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/