Review Article Open Access

From Textural Inpainting to Deep Generative Models: An Extensive Survey of Image Inpainting Techniques

Setika Mehra1, Ayush Dogra2, Bhawna Goyal3, Apoorav Maulik Sharma2 and Ramesh Chandra4
  • 1 Amritsar College of Engineering and Technology, India
  • 2 Panjab University, India
  • 3 Chandigarh University, India
  • 4 NTNU - Norwegian University of Science and Technology, Norway
Journal of Computer Science
Volume 16 No. 1, 2020, 35-49

DOI: https://doi.org/10.3844/jcssp.2020.35.49

Submitted On: 25 November 2019 Published On: 1 January 2020

How to Cite: Mehra, S., Dogra, A., Goyal, B., Sharma, A. M. & Chandra, R. (2020). From Textural Inpainting to Deep Generative Models: An Extensive Survey of Image Inpainting Techniques. Journal of Computer Science, 16(1), 35-49. https://doi.org/10.3844/jcssp.2020.35.49

Abstract

Image inpainting is an evolving discipline of image processing with the objective of reconstructing an image by removing unwanted information, adding missing information or presenting the information appealing to the human visual system. In the presented manuscript, we have exhibited an extensive survey of various image inpainting techniques. The effectiveness of the techniques is together summarized with significant comparisons and assessed by analyzing the merits and demerits. For applicability of image inpainting imparting optimum results in the field of loss concealment, object removal, image restoration or disocclusion, the information from nearby regions is seeked to acquire an image with restored absent information. The inpainted image result can be evaluated using subjective and objective analysis, with emphasis on subjective analysis as a dedicated tool for evaluation.

  • 708 Views
  • 365 Downloads
  • 0 Citations

Download

Keywords

  • Image Inpainting
  • Structural Inpainting
  • Textural Inpainting
  • Partial Differential Equation (PDE)
  • Exemplar-Based Inpainting
  • Deep Generative Models