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

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.

[1]  Pratul P. Srinivasan,et al.  NeRF , 2020, ECCV.

[2]  Nelson L. Max,et al.  Optical Models for Direct Volume Rendering , 1995, IEEE Trans. Vis. Comput. Graph..

[3]  Kai Zhang,et al.  NeRF++: Analyzing and Improving Neural Radiance Fields , 2020, ArXiv.