Global Latent Neural Rendering

arXiv:2312.08338v2 Announce Type: replace
Abstract: A recent trend among generalizable novel view synthesis methods is to learn a rendering operator acting over single camera rays. This approach is promising because it removes the need for explicit volumetric rendering, but it effectively treats target images as collections of independent pixels. Here, we propose to learn a global rendering operator acting over all camera rays jointly. We show that the right representation to enable such rendering is a 5-dimensional plane sweep volume …

abstract acting arxiv cs.cv global images independent learn neural rendering novel pixels rendering synthesis trend type view