Structure-preserving image completion with multi-level dynamic patches

Bowen LIU, Ping LI, Bin SHENG, Yongwei NIE, Enhua WU

Research output: Contribution to journalArticlespeer-review

5 Citations (Scopus)


In this paper, we present a novel structure-preserving image completion approach equipped with dynamic patches. We formulate the image completion problem into an energy minimization framework that accounts for coherence within the hole and global coherence simultaneously. The completion of the hole is achieved through iterative optimizations combined with a multi-scale solution. In order to avoid abnormal structure and disordered texture, we utilize a dynamic patch system to achieve efficient structure restoration. Our dynamic patch system functions in both horizontal and vertical directions of the image pyramid. In the horizontal direction, we conduct a parallel search for multi-size patches in each pyramid level and design a competitive mechanism to select the most suitable patch. In the vertical direction, we use large patches in higher pyramid level to maximize the structure restoration and use small patches in lower pyramid level to reduce computational workload. We test our approach on massive images with complex structure and texture. The results are visually pleasing and preserve nice structure. Apart from effective structure preservation, our approach outperforms previous state-of-the-art methods in time consumption. Copyright © 2017 Springer-Verlag GmbH Germany.
Original languageEnglish
Pages (from-to)85-98
JournalThe Visual Computer
Issue number1
Early online dateOct 2017
Publication statusPublished - Jan 2019


Liu, B., Li, P., Sheng, B., Nie, Y., & Wu, E. (2019). Structure-preserving image completion with multi-level dynamic patches. The Visual Computer, 35(1), 85-98. doi: 10.1007/s00371-017-1454-x


  • Image completion
  • Patch-based approach
  • Dynamic patches
  • Structure preservation
  • Parallel search
  • Multi-scale solution
  • PG student publication


Dive into the research topics of 'Structure-preserving image completion with multi-level dynamic patches'. Together they form a unique fingerprint.