An Approach for Objective Quality Assessment of Image Inpainting Results

Image Inpainting techniques are generally challenging to evaluate objectively due to the lack of comparative data, as a reference image of the new scene, does not exist.. This paper presents an approach that uses our newly released dataset specifically designed to allow objective evaluation of inpainting techniques. In this work we demonstrate how traditional in-painting techniques can be objectively evaluated and compared together with modern deep learning and adversarial approaches. We further demonstrate how an unsupervised technique compares better than deep learning approaches.

[1]  Dayang Rohaya,et al.  A comparative study of different image completion techniques , 2014, 2014 International Conference on Computer and Information Sciences (ICCOINS).

[2]  Sugato Chakravarty,et al.  Methodology for the subjective assessment of the quality of television pictures , 1995 .

[3]  Leon A. Gatys,et al.  A Neural Algorithm of Artistic Style , 2015, ArXiv.

[4]  Hao Li,et al.  High-Resolution Image Inpainting Using Multi-scale Neural Patch Synthesis , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[6]  Haifeng Hu,et al.  Image Inpainting Based on Patch-GANs , 2019, IEEE Access.

[7]  Ruigang Yang,et al.  Stereoscopic inpainting: Joint color and depth completion from stereo images , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[8]  Alexandru Telea,et al.  An Image Inpainting Technique Based on the Fast Marching Method , 2004, J. Graphics, GPU, & Game Tools.

[9]  R. Priyadharsini,et al.  A survey on inpainting techniques , 2016, 2016 International Conference on Electrical, Electronics, and Optimization Techniques (ICEEOT).

[10]  Sung Yong Shin,et al.  On pixel-based texture synthesis by non-parametric sampling , 2006, Comput. Graph..

[11]  Guillermo Sapiro,et al.  Navier-stokes, fluid dynamics, and image and video inpainting , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[12]  Ting-Chun Wang,et al.  Image Inpainting for Irregular Holes Using Partial Convolutions , 2018, ECCV.

[13]  Patrick Pérez,et al.  Region filling and object removal by exemplar-based image inpainting , 2004, IEEE Transactions on Image Processing.

[14]  Azeddine Beghdadi,et al.  Inpainted image quality assessment , 2013, European Workshop on Visual Information Processing (EUVIP).

[15]  Minh N. Do,et al.  Semantic Image Inpainting with Deep Generative Models , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Alexei A. Efros,et al.  Context Encoders: Feature Learning by Inpainting , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Tony F. Chan,et al.  Nontexture Inpainting by Curvature-Driven Diffusions , 2001, J. Vis. Commun. Image Represent..

[19]  Mahima Vuppuluri,et al.  Survey on Generative Adversarial Networks , 2017 .

[20]  Hiroshi Ishikawa,et al.  Globally and locally consistent image completion , 2017, ACM Trans. Graph..

[21]  Carl James Debono,et al.  Monoscopic inpainting approach using depth information , 2016, 2016 18th Mediterranean Electrotechnical Conference (MELECON).