SpotlessSplats: Ignoring Distractors in 3D Gaussian Splatting
This addresses the issue of requiring controlled environments for 3D Gaussian Splatting, making it more practical for real-world applications, though it appears incremental as it builds on existing 3DGS methods.
The paper tackles the problem of 3D reconstruction in real-world captures with transient distractors using SpotlessSplats, which leverages pre-trained features and robust optimization to ignore these distractors, achieving state-of-the-art reconstruction quality on casual captures.
3D Gaussian Splatting (3DGS) is a promising technique for 3D reconstruction, offering efficient training and rendering speeds, making it suitable for real-time 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. Additional results available at: https://spotlesssplats.github.io