FACT-GS: Frequency-Aligned Complexity-Aware Texture Reparameterization for 2D Gaussian Splatting

2025-11-28

AI Summary

Existing Gaussian splatting texture rendering employs uniform grid sampling, which fails to adapt to local visual complexity—resulting in loss of high-frequency detail and wasteful oversampling in smooth regions. To address this, we propose a frequency-aligned, complexity-aware reparameterization framework: the first to introduce adaptive sampling theory into 2D Gaussian lattice texture modeling. Our method employs a learnable deformation field to dynamically modulate sampling density across the texture domain, with Jacobian regularization ensuring differentiability and geometric consistency. This enables non-uniform, visual-frequency-driven texture resource allocation on a fixed-resolution parameter grid. Experiments demonstrate that, under identical parameter budgets, our approach significantly improves high-frequency detail reconstruction, reduces redundant sampling, enhances texture space utilization, and maintains real-time rendering performance.

Technology Category

Search and Optimization: Sampling/Simulation-based SearchComputer Vision: Diffusion Models for VisionMachine Learning: Learning with Manifolds

Application Category

User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendationSearch and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for rankingEconomics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Realistic scene appearance modeling has advanced rapidly with Gaussian Splatting, which enables real-time, high-quality rendering. Recent advances introduced per-primitive textures that incorporate spatial color variations within each Gaussian, improving their expressiveness. However, texture-based Gaussians parameterize appearance with a uniform per-Gaussian sampling grid, allocating equal sampling density regardless of local visual complexity. This leads to inefficient texture space utilization, where high-frequency regions are under-sampled and smooth regions waste capacity, causing blurred appearance and loss of fine structural detail. We introduce FACT-GS, a Frequency-Aligned Complexity-aware Texture Gaussian Splatting framework that allocates texture sampling density according to local visual frequency. Grounded in adaptive sampling theory, FACT-GS reformulates texture parameterization as a differentiable sampling-density allocation problem, replacing the uniform textures with a learnable frequency-aware allocation strategy implemented via a deformation field whose Jacobian modulates local sampling density. Built on 2D Gaussian Splatting, FACT-GS performs non-uniform sampling on fixed-resolution texture grids, preserving real-time performance while recovering sharper high-frequency details under the same parameter budget.

Problem

• Optimizes texture sampling density for Gaussian splatting
• Addresses inefficient texture space utilization in rendering
• Enhances high-frequency detail preservation in real-time graphics

Innovation

• Frequency-aligned texture sampling density allocation
• Differentiable sampling-density allocation via deformation field
• Non-uniform sampling on fixed-resolution texture grids