3D Gaussian Splatting (3DGS) is a technique to create high-quality, real-time 3D scenes from images. This method often produces visual artifacts known as floaters--nearly transparent, disconnected elements that drift in space away from the actual surface. This geometric inaccuracy undermines the reliability of these models for practical applications, which is critical. To address this issue, we introduce TIDI-GS, a new training framework designed to eliminate these floaters. A key benefit of our approach is that it functions as a lightweight plugin for the standard 3DGS pipeline, requiring no major architectural changes and adding minimal overhead to the training process. The core of our method is a floater pruning algorithm--TIDI--that identifies and removes floaters based on several criteria: their consistency across multiple viewpoints, their spatial relationship to other elements, and an importance score learned during training. The framework includes a mechanism to preserve fine details, ensuring that important high-frequency elements are not mistakenly removed. This targeted cleanup is supported by a monocular depth-based loss function that helps improve the overall geometric structure of the scene. Our experiments demonstrate that TIDI-GS improves both the perceptual quality and geometric integrity of reconstructions, transforming them into robust digital assets, suitable for high-fidelity applications.

翻译：3D高斯泼溅（3DGS）是一种从图像创建高质量、实时3D场景的技术。该方法常会产生被称为漂浮物的视觉伪影——即近乎透明、与真实表面分离并在空间中漂移的离散元素。这种几何不准确性削弱了此类模型在实际应用中的可靠性，而可靠性至关重要。为解决此问题，我们提出了TIDI-GS，一种旨在消除这些漂浮物的新型训练框架。我们方法的一个关键优势在于，它可作为标准3DGS流程的轻量级插件运行，无需重大架构改动，且对训练过程仅增加极小开销。我们方法的核心是一个漂浮物剪枝算法——TIDI——该算法基于多个标准识别并移除漂浮物：它们在多视角下的一致性、与其他元素的空间关系，以及在训练过程中学习到的重要性分数。该框架包含一种保留精细细节的机制，确保重要的高频元素不会被误移除。这种针对性清理得到了一项基于单目深度的损失函数的支持，该函数有助于改善场景的整体几何结构。我们的实验表明，TIDI-GS同时提升了重建结果的感知质量和几何完整性，将其转化为适用于高保真应用的鲁棒数字资产。