Universal Framework for Joint Image Restoration and 3D Body Reconstruction

Recent works have demonstrated excellent state-of-the-art achievements in image restoration and 3D body reconstruction from an input image. The 3D body reconstruction task, however, relies heavily on the input image's quality. A straightforward way to solve this issue is by generating vast degr...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access 2021, Vol.9, p.162543-162552
Main Authors: Lumentut, Jonathan Samuel, Marchellus, Matthew, Santoso, Joshua, Kim, Tae Hyun, Chang, Ju Yong, Park, In Kyu
Format: Article
Language:English
Subjects:
3D body reconstruction
Datasets
deblur
denoising
Image quality
Image reconstruction
Image restoration
meta-learning
Neural networks
Noise measurement
Noise reduction
Obsolescence
pseudo-data
Restoration
self-adaptive
super-resolution
Task analysis
Testing time
Three dimensional bodies
Three-dimensional displays
Training
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:Recent works have demonstrated excellent state-of-the-art achievements in image restoration and 3D body reconstruction from an input image. The 3D body reconstruction task, however, relies heavily on the input image's quality. A straightforward way to solve this issue is by generating vast degraded datasets and using them in a re-finetuned or newly-crafted body reconstruction network. However, in future usage, these datasets may become obsolete, leaving the newly-crafted network outdated. Unlike this approach, we design a universal framework that is able to utilize prior state-of-the-art restoration works and then self-boosts their performances during test-time while jointly carrying out the 3D body reconstruction. The self-boosting mechanism is adopted via test-time parameter adaptation capable of handling various types of degradation. To accommodate, we also propose a strategy that generates pseudo-data on the fly during test-time, allowing both restoration and reconstruction modules to be learned in a self-supervised manner. With this advantage, the universal framework intelligently enhances the performance without any new dataset or new neural network model involvement. Our experimental results show that using the proposed framework and pseudo-data strategies significantly improves the performances of both scenarios.
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2021.3132148