no code implementations • 5 May 2023 • Hyojoon Park, Sangeetha Grama Srinivasan, Matthew Cong, Doyub Kim, Byungsoo Kim, Jonathan Swartz, Ken Museth, Eftychios Sifakis
We present a neural network-based simulation super-resolution framework that can efficiently and realistically enhance a facial performance produced by a low-cost, realtime physics-based simulation to a level of detail that closely approximates that of a reference-quality off-line simulator with much higher resolution (26x element count in our examples) and accurate physical modeling.
no code implementations • 15 Feb 2021 • He Chen, Hyojoon Park, Kutay Macit, Ladislav Kavan
The key idea behind our system is a new type of motion capture suit which contains a special pattern with checkerboard-like corners and two-letter codes.