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

page 1

page 6

page 7

research
07/06/2023

EffLiFe: Efficient Light Field Generation via Hierarchical Sparse Gradient Descent

With the rise of Extended Reality (XR) technology, there is a growing ne...
research
07/26/2021

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

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

Realistic Defocus Blur for Multiplane Computer-Generated Holography

This paper introduces a new multiplane CGH computation method to reconst...
research
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...
research
08/31/2017

Model based learning for accelerated, limited-view 3D photoacoustic tomography

Recent advances in deep learning for tomographic reconstructions have sh...

Please sign up or login with your details

Forgot password? Click here to reset