RobustNeRF: Ignoring Distractors with Robust Losses
This addresses artifacts in 3D scene reconstruction for computer vision applications, but is an incremental improvement focused on optimization rather than a new paradigm.
The paper tackles the problem of artifacts in Neural Radiance Fields (NeRF) caused by distractors like moving objects or lighting variations, and shows that using robust losses to model these as outliers improves scene quality over baselines on synthetic and real-world scenes.
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.