View Synthesis In Casually Captured Scenes Using a Cylindrical Neural Radiance Field With Exposure Compensation
暂无分享,去创建一个
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.