University of Illinois computer science professor Yizhou Yu received a Best Paper Award for his work to recreate physical imperfections in scanned models of a human hand. The work, “Controllable Hand Deformation from Sparse Examples with Rich Details” received the Best Paper award at the ACM SIGGRAPH/Eurographics Symposium on Computer Animation (SCA 2011).
“Recent advances in laser scanning technology have made it possible to faithfully scan a real object with tiny geometric details, such as pores and wrinkles,” said Yu in the paper. “However, a faithful digital model should not only capture static details of the real counterpart, but be able to reproduce the deformed versions of such details.”
The team used models of a human hand to test their approach. Hand models tend to be among the most challenging, because human hands have such a large degree of freedom of motion, and highly deformable wrinkles.
The team developed data-driven methods to reproduce such deformities both on a large-scale, and in high resolution. The team’s framework was capable of synthesizing high-resolution hand mesh animations with rich and varying details from as few as 14 training examples. The team’s approach is able to be applied both to keyframe animation systems as well as performance-driven animation.
The papers coauthors included Haoda Huang and Xin Tong (Microsoft Research Asia), Ling Zhao and Yue Qi (Beihang University), and KangKang Yin (National University of Singapore).