RobustNeRF：利用鲁棒损失忽略干扰物
RobustNeRF: Ignoring Distractors with Robust Losses
AI总结：
针对NeRF场景中干扰物导致的伪影问题，提出将训练数据中的干扰物建模为优化问题的异常值进行鲁棒估计，成功移除异常值并提升合成与真实场景下的新视角合成质量。
摘要：
给定静态场景的多视角标定图像，神经辐射场（NeRF）在合成新视角方面表现优异。当场景包含在图像采集期间不持久的干扰物（移动物体、光照变化、阴影）时，伪影会表现为视角依赖效应或“悬浮物”。为应对干扰物，我们提倡在NeRF训练中采用一种鲁棒估计形式，将训练数据中的干扰物建模为优化问题的异常值。我们的方法成功从场景中移除了异常值，并在合成和真实世界场景上改进了基线。该技术易于整合到现代NeRF框架中，且超参数很少。它不假设关于干扰物类型的先验知识，而是专注于优化问题，而非预处理或建模瞬态物体。更多结果见我们的页面 https://robustnerf.github.io。
英文摘要：
Neural radiance fields (NeRF) excel at synthesizing new views given multi-view, calibrated images of a static scene. When scenes include distractors, which are not persistent during image capture (moving objects, lighting variations, shadows), artifacts appear as view-dependent effects or 'floaters'. To cope with distractors, we advocate a form of robust estimation for NeRF training, modeling distractors in training data as outliers of an optimization problem. Our method successfully removes outliers from a scene and improves upon our baselines, on synthetic and real-world scenes. Our technique is simple to incorporate in modern NeRF frameworks, with few hyper-parameters. It does not assume a priori knowledge of the types of distractors, and is instead focused on the optimization problem rather than pre-processing or modeling transient objects. More results on our page https://robustnerf.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。
