This $600,000 Project Grant awarded by the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) Federal Grant Program (CFDA 47.070) aims to develop a novel, resolution-independent and discontinuity-preserving neural image representation. The project at the University of California, San Diego (UCSD) seeks to create a 2D neural representation capable of accurately capturing image discontinuities, with extensions to higher dimensional signals like videos and light fields. Key research objectives include efficient fitting techniques, accelerated training, and reduced memory requirements. The project will explore applications of this representation in areas like image rendering, physics-informed neural networks, and super-resolution, with the potential to transform computer graphics and computational photography. The award has a performance period from July 2024 to June 2027.
Generated 1/28/25, 7:19 AM