SpotLessSplats: Ignoring Distractors in 3D Gaussian Splatting

3D Gaussian Splatting (3DGS) is a promising technique for 3D reconstruction, offering efficient training and rendering speeds, making it suitable for realtime applications. However, current methods require highly controlled environments—no moving people or wind-blown elements, and consistent lighting—to meet the inter-view consistency assumption of 3DGS. This makes reconstruction of real-world captures problematic. We present SpotLessSplats, an approach that leverages pre-trained and general-purpose features coupled with robust optimization to effectively ignore transient distractors. Our method achieves state-of-the-art reconstruction quality both visually and quantitatively, on casual captures三维高斯溅射（3D Gaussian Splatting，3DGS）是一种极具潜力的三维重建技术，凭借高效的训练与渲染速度，适用于实时应用场景。然而，现有方法需要高度受控的环境——无移动行人、无受风扰动的物体，且光照稳定——以满足三维高斯溅射的视图间一致性假设，这使得对真实世界采集数据的重建任务面临诸多挑战。为此我们提出SpotLessSplats方法，该方法借助预训练通用特征结合鲁棒优化技术，可有效忽略瞬态干扰物。该方法在非受控随手采集的数据上，无论是视觉表现还是量化指标均达到了当前最优的重建质量。