Skip to content

Learning-based texture synthesis and automatic inpainting using support vector machines

Research output: Contribution to journalArticle

Texture synthesis methods based on patch sampling and pasting that can generate realistic textures with a similar appearance to a small sample. However, the sample usually has to be used throughout the synthesis stage. In contrast, the learnt representation of the textures are more compact and discriminative, and can also yield good synthesis results. In this paper, we introduce a learnt approach for texture synthesis based on Support Vector Machines (SVM). This approach benefits from the merit of SVM that the sample texture pattern is learnt using a model, and the sample itself can be discarded during the synthesis stage; the approach is also used to synthesize 3D surface textures. Experimental results show that our approach is particularly effective in modeling and synthesizing nearregular or regular textures, which are difficult to achieve using traditional parametric texture synthesis methods. We further apply the proposed approach to constrained texture synthesis, image extrapolation and texture inpainting. For texture inpainting, we especially develop a new method for automatically detecting holes in textures without the requirement of human intervention. Our approach yields promising results for the three tasks.
Original languageEnglish
JournalIEEE Transactions on Industrial Electronics
Early online date24 Aug 2018
Publication statusEarly online - 24 Aug 2018


  • Learning-Based Texture Synthesis and Automatic Inpainting Using SVM_postprint

    Rights statement: © © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

    Accepted author manuscript (Post-print), 1.56 MB, PDF document

Relations Get citation (various referencing formats)

ID: 11145442