DeepView: View Synthesis with Learned Gradient Descent

June 18, 2019 · Entered Twilight · 🏛 Computer Vision and Pattern Recognition

"No code URL or promise found in abstract"
"Derived repo from GitHub Pages (backfill)"

Evidence collected by the PWNC Scanner

Repo contents: _config.yml, _layouts, ablation, assets, compLFMPI, index.html, index.md, iteration, mpi, results_kalantari, results_spaces, thumbs, training_details.pdf, vr50_images

Authors John Flynn, Michael Broxton, Paul Debevec, Matthew DuVall, Graham Fyffe, Ryan Overbeck, Noah Snavely, Richard Tucker arXiv ID 1906.07316 Category cs.CV: Computer Vision Cross-listed cs.GR, cs.LG, eess.IV Citations 477 Venue Computer Vision and Pattern Recognition Repository https://github.com/augmentedperception/deepview ⭐ 33 Last Checked 8 days ago

Abstract

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.