Robust Image Completion via Deep Feature Transformations
Open Access
- 14 August 2019
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 113916-113930
Abstract
For many practical applications, it is essential to address both geometric corrections and missing information reconstruction of face images and natural images. However, it is unfavorable to separate the problem into two sub-tasks due to error accumulations of sequential tasks. In this paper, we propose a novel robust missing information reconstruction framework via deep feature transformations to simultaneously address both geometric corrections and image completion. Specifically, our proposed framework realizes multiple channel spatial transformations to tackle geometric corrections, and address image completion through non-linear features projections. The flow of our framework includes deep feature extraction, feature enhancement, feature projection, and feature refinement, where deep features are extracted and learnt to achieve robust image completion. Experimental results show the superior performance of our framework for both face images and natural images in various databases. Compared with the conventional approaches approach to split the problem into two sub-tasks, including image inpainting and spatial transformation, our proposed framework achieves a number of advantages, including i) an unified framework to automatically correct the geometric distortions and to reconstruct the missing information simultaneously and ii) achieving much better visual quality for those recovered images.Keywords
Funding Information
- National Natural Science Foundation of China (61620106008, 61602312)
- Shenzhen Commission for Scientific Research & Innovations (JCYJ20160226191842793)
This publication has 50 references indexed in Scilit:
- Image Completion Approaches Using the Statistics of Similar PatchesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Image Inpainting : Overview and Recent AdvancesIEEE Signal Processing Magazine, 2013
- A Unified Learning Framework for Single Image Super-ResolutionIEEE Transactions on Neural Networks and Learning Systems, 2013
- Single Image Super-Resolution With Multiscale Similarity LearningIEEE Transactions on Neural Networks and Learning Systems, 2013
- Multi-column deep neural network for traffic sign classificationNeural Networks, 2012
- Statistics of Patch Offsets for Image Completion2012
- PatchMatchACM Transactions on Graphics, 2009
- Gaps‐fill of SLC‐off Landsat ETM+ satellite image using a geostatistical approachInternational Journal of Remote Sensing, 2007
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- Mathematical Models for Local Nontexture InpaintingsSIAM Journal on Applied Mathematics, 2002