Low-Rank Matrix Completion to Reconstruct Incomplete Rendering Images

Path tracing provides photo-realistic rendering in many applications but intermediate previsualization often suffers from distracting noise. Since the fundamental underlying problem is insufficient samples, we exploit the coherence of the visual signal to reconstruct missing samples, using a low-ran...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on visualization and computer graphics 2018-08, Vol.24 (8), p.2353-2365
Main Authors: Liu, Ping, Lewis, John, Rhee, Taehyun
Format: Article
Language:English
Subjects:
Artificial neural networks
convolutional neural network
Image coding
Image reconstruction
matrix completion
Minimization
Monte Carlo methods
Neural networks
nuclear norm minimization
path-tracing
Pixels
Previsualisation
Rendering
Rendering (computer graphics)
sampling and reconstruction
Visual signals
Visualization
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Path tracing provides photo-realistic rendering in many applications but intermediate previsualization often suffers from distracting noise. Since the fundamental underlying problem is insufficient samples, we exploit the coherence of the visual signal to reconstruct missing samples, using a low-rank matrix completion framework. We present novel methods to construct low rank matrices for incomplete images including missing pixel, missing sub-pixel, and multi-frame scenarios. A convolutional neural network provides fast pre-completion for initialising missing values, and subsequent weighted nuclear norm minimisation (WNNM) with a parameter adjustment strategy (PAWNNM) efficiently recovers missing values even in high frequency details. The result shows better visual quality than recent methods including compressed sensing based reconstruction.
ISSN:1077-2626
1941-0506
DOI:10.1109/TVCG.2017.2722414