Project Grant 2549260

The National Science Foundation Division of Information and Intelligent Systems awarded The University of Central Florida Board of Trustees $240,000 on October 1, 2026, under the Computer and Information Science and Engineering program (CFDA 47.070) to develop AI-native holographic communication technology that reduces the computational and bandwidth requirements for transmitting high-fidelity 3D holograms across consumer devices.

The project advances a generative holographic codec integrating 3D Gaussian splatting, vector quantization, and masked encoder-decoder learning to capture subjects using one or a few standard cameras, transmit a compact set of digital cues, and reconstruct 3D holograms on smartphones, smart glasses, and headsets. Work includes designing generalizable codecs for sparse multi-view and single-view inputs with built-in recovery mechanisms; developing sparse computing methods for resource-constrained edge devices using heterogeneity-aware global structured pruning, mixed-precision quantization, and pose- and point-aware attention mechanisms; and creating adaptive control via layered refinement and reinforcement learning to dynamically balance quality, bandwidth, latency, memory, and device hardware constraints. The framework will be evaluated across wireless testbeds, long-distance network links, and large-scale simulations to broaden access to immersive communication in remote healthcare, interactive classrooms, emergency response training, workforce development, collaborative design, and the digital arts.

Work is performed in Alafaya, Florida. The period of performance runs October 1, 2026, through September 30, 2029.