Human object inpainting using manifold learning-based posture sequence estimation

Chih Hung Ling*, Yu Ming Liang, Chia Wen Lin, Yong-Sheng Chen, Hong Yuan Mark Liao

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

10 Scopus citations


We propose a human object inpainting scheme that divides the process into three steps: 1) human posture synthesis; 2) graphical model construction; and 3) posture sequence estimation. Human posture synthesis is used to enrich the number of postures in the database, after which all the postures are used to build a graphical model that can estimate the motion tendency of an object. We also introduce two constraints to confine the motion continuity property. The first constraint limits the maximum search distance if a trajectory in the graphical model is discontinuous, and the second confines the search direction in order to maintain the tendency of an object's motion. We perform both forward and backward predictions to derive local optimal solutions. Then, to compute an overall best solution, we apply the Markov random field model and take the potential trajectory with the maximum total probability as the final result. The proposed posture sequence estimation model can help identify a set of suitable postures from the posture database to restore damaged/missing postures. It can also make a reconstructed motion sequence look continuous.

Original languageEnglish
Article number5779735
Pages (from-to)3124-3135
Number of pages12
JournalIEEE Transactions on Image Processing
Issue number11
StatePublished - 1 Nov 2011


  • Dimensionality reduction
  • isomap
  • manifold learning
  • object completion
  • video inpainting


Dive into the research topics of 'Human object inpainting using manifold learning-based posture sequence estimation'. Together they form a unique fingerprint.

Cite this