RobustSplat：解耦密度化與動態處理，實現無瞬態干擾的3D高斯散射

摘要

3D高斯溅射（3DGS）因其在新视角合成和3D建模中的实时、照片级真实感渲染而备受关注。然而，现有方法在准确建模受瞬态物体影响的场景时存在困难，导致渲染图像中出现伪影。我们发现，高斯密度化过程虽然在增强场景细节捕捉方面效果显著，却无意中通过生成额外的高斯分布来模拟瞬态干扰，从而加剧了这些伪影。为解决这一问题，我们提出了RobustSplat，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高斯增长策略，该策略优先优化静态场景结构，再允许高斯分裂/克隆，从而在早期优化中减少对瞬态物体的过拟合。其次，我们设计了一种尺度级联掩码自举方法，该方法首先利用较低分辨率的特征相似性监督进行可靠的初始瞬态掩码估计，充分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进行的大量实验表明，我们的方法优于现有方法，清晰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/。

English

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/.

RobustSplat：解耦密度化與動態處理，實現無瞬態干擾的3D高斯散射

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

摘要

Support