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

2026-03-26

AI Summary

This work addresses the scalability limitation of existing feed-forward 3D Gaussian splatting methods, whose pixel-aligned primitives grow quadratically with output resolution, hindering efficient 4K novel view synthesis. To overcome this bottleneck, we propose LGTM, a framework that introduces per-primitive texture mapping into feed-forward Gaussian splatting for the first time. By predicting compact geometric primitives and assigning learned textures to them, LGTM decouples geometric complexity from rendering resolution. This design eliminates the need for per-scene optimization and drastically reduces the number of required Gaussians while enabling high-quality 4K novel view synthesis, thereby breaking the resolution scalability barrier in feed-forward Gaussian splatting.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Computer Vision: 3D Computer Vision
• Search and Optimization: Learning to Search

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

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/

Problem

• Gaussian Splatting
• resolution scaling
• feed-forward
• novel view synthesis
• high-resolution rendering

Innovation

• Gaussian Splatting
• feed-forward rendering
• texture mapping
• 4K novel view synthesis
• resolution scalability