DeepView: View Synthesis with Learned Gradient Descent

06/18/2019
by   John Flynn, et al.
5

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.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 6

page 7

07/26/2021

NeLF: Neural Light-transport Field for Portrait View Synthesis and Relighting

Human portraits exhibit various appearances when observed from different...
05/14/2022

RTMV: A Ray-Traced Multi-View Synthetic Dataset for Novel View Synthesis

We present a large-scale synthetic dataset for novel view synthesis cons...
02/12/2020

Learning light field synthesis with Multi-Plane Images: scene encoding as a recurrent segmentation task

In this paper we address the problem of view synthesis from large baseli...
03/09/2021

NeX: Real-time View Synthesis with Neural Basis Expansion

We present NeX, a new approach to novel view synthesis based on enhancem...
05/14/2022

Realistic Defocus Blur for Multiplane Computer-Generated Holography

This paper introduces a new multiplane CGH computation method to reconst...
01/15/2017

Light Source Estimation with Analytical Path-tracing

We present a novel algorithm for light source estimation in scenes recon...
02/01/2011

Smart depth of field optimization applied to a robotised view camera

The great flexibility of a view camera allows to take high quality photo...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.