MSR is continuing its research in creating the perfect photographic, this time focusing on having the perfect hair.  Lvdi Wang has been working for the past year and a half on improving the appearance of hair in digital images. Wang and his colleagues will be demonstrating their latest progress by delivering a paper called Dynamic Hair Manipulation in Images and Videos, co-authored by Zhejiang University’s Menglei Chai, Yanlin Weng, Xiaogang Jin, and Kun Zhou, along with Wang. The paper outlines a new, single-view hair-modeling technique for generating visually and physically plausible 3-D hair models achieved with only modest user interaction. The work creates hair models that visually match an original input image. “We proposed a new method for creating a 3-D hair model from just one single photograph or short video,” Wang explains. “Such a model contains tens of thousands of individual hair strands and allows the user to manipulate hair ...

Read More →