PoseShop: Human Image Database Construction and Personalized Content Synthesis

Tao Chen1, Ping Tan2, Li-Qian Ma1, Ming-Ming Cheng1, Ariel Shamir3, Shi-Min Hu1
1Tsinghua University
2National University of Singapore
3The Interdisciplinary Center

Abstract: We present PoseShop°™a pipeline to construct segmented human image database with minimal manual intervention. By downloading, analyzing, and filtering massive amounts of human images from the Internet, we achieve a database which contains 400 thousands human figures that are segmented out of their background. The human figures are organized based on action semantic, clothes attributes, and indexed by the shape of their poses. They can be queried using either silhouette sketch or a skeleton to find a given pose. We demonstrate applications for this database for multiframe personalized content synthesis in the form of comic-strips, where the main character is the user or his/her friends. We address the two challenges of such synthesis, namely personalization and consistency over a set of frames, by introducing head swapping and clothes swapping techniques. We also demonstrate an action correlation analysis application to show the usefulness of the database for vision application.

Paper: [PDF 16.6M].
Supplemental Document: [PDF 18.5M].
Supplemental Video: [AVI 48.4M].
Library: [please fill the form].

Bibtex: @article{Chen:2013:PHI:2478571.2479160,
author = {Chen, Tao and Tan, Ping and Ma, Li-Qian and Cheng, Ming-Ming and Shamir, Ariel and Hu, Shi-Min},
title = {PoseShop: Human Image Database Construction and Personalized Content Synthesis},
journal = {IEEE Transactions on Visualization and Computer Graphics},
volume = {19},
number = {5},
month = may,
year = {2013},
issn = {1077-2626},
pages = {824--837},
numpages = {14},
url = {http://dx.doi.org/10.1109/TVCG.2012.148},
doi = {10.1109/TVCG.2012.148},
acmid = {2479160},
publisher = {IEEE Educational Activities Department},
address = {Piscataway, NJ, USA},
keywords = {Humans,Skin,Image segmentation,Image databases,Image color analysis,Shape,image composition,Image database},