We present a novel approach to view synthesis using multiplane images (MPIs). Building on recent advances in learned gradient descent, our algorithm generates an MPI from a set of sparse camera viewpoints. The resulting method incorporates occlusion reasoning, improving performance on challenging scene features such as object boundaries, lighting reflections, thin structures, and scenes with high depth complexity. We show that our method achieves high-quality, state-of-the-art results on two datasets: the Kalantari light field dataset, and a new camera array dataset, Spaces, which we make publicly available.
@article{arxiv.1906.07316,
title = {DeepView: View Synthesis with Learned Gradient Descent},
author = {John Flynn and Michael Broxton and Paul Debevec and Matthew DuVall and Graham Fyffe and Ryan Overbeck and Noah Snavely and Richard Tucker},
journal= {arXiv preprint arXiv:1906.07316},
year = {2019}
}
Comments
See https://augmentedperception.github.io/deepview/ for more results, video and an interactive viewer