CMU Collaborates with Fujitsu Researchers on Breakthrough in Dynamic 3D Structure Representation

“Working with 2D images to create a 3D structure is a complex process that requires a deep understanding of how to handle deformations and changes. DyLiN matched state-of-the-art methods in terms of visual fidelity while being 25-71 times faster computationally. “The strides made by DyLiN and CoDyLiN mark an exciting progression towards real-time volumetric rendering and animation,” Jeni said. DyLiN and CoDyLiN can accurately render and analyze changes in human movement within a virtual 3D space based on 2D images. The team presented its paper, “DyLiN: Making Light Field Networks Dynamic,” in June at the Conference on Vision and Pattern Recognition.