View Synthesis in Casually Captured Scenes Using a Cylindrical Neural Radiance Field With Exposure Compensation

摘要

We extend Neural Radiance Fields (NeRF) with a cylindrical parameterization that enables rendering photorealistic novel views of 360° outward facing scenes. We further introduce a learned exposure compensation parameter to account for the varying exposure in training images that may occur from casually capturing a scene. We evaluate our method on a variety of 360° casually captured scenes.