标题： 鲁棒点积：解耦密度化和动态以实现无瞬态的3DGS 显示英文标题

标题： RobustSplat: Decoupling Densification and Dynamics for Transient-Free 3DGS

摘要： 3D高斯点云（3DGS）因其在新视角合成和3D建模中的实时、逼真渲染而受到广泛关注。 然而，现有方法在准确建模受瞬时物体影响的场景方面存在困难，导致渲染图像中出现伪影。 我们发现，高斯密度化过程虽然增强了场景细节的捕捉，但无意中通过生成额外的高斯模型来模拟瞬时干扰，从而导致这些伪影。 为了解决这个问题，我们提出了RobustSplat，这是一种基于两个关键设计的鲁棒解决方案。 首先，我们引入了一种延迟的高斯增长策略，在允许高斯分裂/克隆之前优先优化静态场景结构，从而减轻早期优化中对瞬时物体的过拟合。 其次，我们设计了一种尺度级联掩码自举方法，首先利用低分辨率特征相似性监督进行可靠的初始瞬时掩码估计，利用其更强的语义一致性和对噪声的鲁棒性，然后逐步过渡到高分辨率监督以实现更精确的掩码预测。 在多个具有挑战性的数据集上的大量实验表明，我们的方法优于现有方法，清楚地展示了我们方法的鲁棒性和有效性。 我们的项目页面是https://fcyycf.github.io/RobustSplat/。 显示英文摘要

摘要： 3D Gaussian Splatting (3DGS) has gained significant attention for its real-time, photo-realistic rendering in novel-view synthesis and 3D modeling. However, existing methods struggle with accurately modeling scenes affected by transient objects, leading to artifacts in the rendered images. We identify that the Gaussian densification process, while enhancing scene detail capture, unintentionally contributes to these artifacts by growing additional Gaussians that model transient disturbances. To address this, we propose RobustSplat, a robust solution based on two critical designs. First, we introduce a delayed Gaussian growth strategy that prioritizes optimizing static scene structure before allowing Gaussian splitting/cloning, mitigating overfitting to transient objects in early optimization. Second, we design a scale-cascaded mask bootstrapping approach that first leverages lower-resolution feature similarity supervision for reliable initial transient mask estimation, taking advantage of its stronger semantic consistency and robustness to noise, and then progresses to high-resolution supervision to achieve more precise mask prediction. Extensive experiments on multiple challenging datasets show that our method outperforms existing methods, clearly demonstrating the robustness and effectiveness of our method. Our project page is https://fcyycf.github.io/RobustSplat/.