A Sampling Approach to Generating Closely Interacting 3D Pose-pairs from 2D Annotations

Kangxue Yin, Hui Huang, Edmond Ho, Hao Wang, Taku Komura, Daniel Cohen-Or, Hao Zhang

Research output: Contribution to journalArticlepeer-review

4 Citations (Scopus)
12 Downloads (Pure)


We introduce a data-driven method to generate a large number of plausible, closely interacting 3D human pose-pairs, for a given motion category, e.g., wrestling or salsa dance. With much difficulty in acquiring close interactions using 3D sensors, our approach utilizes abundant existing video data which cover many human activities. Instead of treating the data generation problem as one of reconstruction, either through 3D acquisition or direct 2D-to-3D data lifting from video annotations, we present a solution based on Markov Chain Monte Carlo (MCMC) sampling. With a focus on efficient sampling over the space of close interactions, rather than pose spaces, we develop a novel representation called interaction coordinates (IC) to encode both poses and their interactions in an integrated manner. Plausibility of a 3D pose-pair is then defined based on the ICs and with respect to the annotated 2D pose-pairs from video. We show that our sampling-based approach is able to efficiently synthesize a large volume of plausible, closely interacting 3D pose-pairs which provide a good coverage of the input 2D pose-pairs.
Original languageEnglish
Pages (from-to)2217-2227
Number of pages11
JournalIEEE Transactions on Visualization and Computer Graphics
Issue number6
Early online date1 May 2018
Publication statusPublished - 1 Jun 2019


Dive into the research topics of 'A Sampling Approach to Generating Closely Interacting 3D Pose-pairs from 2D Annotations'. Together they form a unique fingerprint.

Cite this