DAV-GSWT: Diffusion-Active-View Sampling for Data-Efficient Gaussian Splatting Wang Tiles

TL;DR

DAV-GSWT introduces a data-efficient method combining diffusion priors and active sampling to generate high-quality Gaussian Splatting Wang Tiles from minimal data, enabling scalable photorealistic 3D rendering.

Contribution

It presents a novel framework that reduces data requirements for generating seamless 3D environment tiles using diffusion models and active view selection.

Findings

Significantly reduces data needed for high-fidelity 3D tiles

Maintains visual quality with minimal input observations

Enables scalable virtual environment synthesis

Abstract

The emergence of 3D Gaussian Splatting has fundamentally redefined the capabilities of photorealistic neural rendering by enabling high-throughput synthesis of complex environments. While procedural methods like Wang Tiles have recently been integrated to facilitate the generation of expansive landscapes, these systems typically remain constrained by a reliance on densely sampled exemplar reconstructions. We present DAV-GSWT, a data-efficient framework that leverages diffusion priors and active view sampling to synthesize high-fidelity Gaussian Splatting Wang Tiles from minimal input observations. By integrating a hierarchical uncertainty quantification mechanism with generative diffusion models, our approach autonomously identifies the most informative viewpoints while hallucinating missing structural details to ensure seamless tile transitions. Experimental results indicate that our system significantly reduces the required data volume while maintaining the visual integrity and interactive performance necessary for large-scale virtual environments.