SpotlessSplats：在3D Gaussian Splatting中忽略干扰因素
SpotlessSplats: Ignoring Distractors in 3D Gaussian Splatting
AI总结：
本文提出SpotLessSplats方法，利用预训练通用特征结合鲁棒优化，有效忽略3D Gaussian Splatting中的瞬态干扰因素，在随意捕获的真实场景中实现了最先进的3D重建质量。
摘要：
3D Gaussian Splatting (3DGS) 是一种极具前景的3D重建技术，提供高效的训练和渲染速度，适合实时应用。然而，当前方法需要高度受控的环境（无移动人员或风吹元素，以及一致的光照）以满足3DGS的视图间一致性假设。这使得真实世界捕获的重建存在问题。我们提出了SpotLessSplats，这是一种利用预训练的通用特征结合鲁棒优化来有效忽略瞬态干扰因素的方法。我们的方法在随意捕获的数据上，在视觉和定量方面都实现了最先进的重建质量。更多结果请见：https://spotlesssplats.github.io
英文摘要：
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
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
