Project Grant 2551340
- The National Science Foundation Division of Computing and Communication Foundations awarded Cornell University $300,000 on October 1, 2026, under the Computer and Information Science and Engineering program (CFDA 47.070) to develop a machine-learning framework for neural light transport and material representation in computer graphics. The project, performed in Ithaca, New York through September 30, 2029, addresses the computational complexity of realistic image synthesis by learning how objects...
- This four-year, $400,000 Project Grant from the National Science Foundation's Computer and Information Science and Engineering program will fund the development of new neural material models for more realistic computer graphics at the University of California, San Diego. Specifically, the university researchers will build machine learning-based models to more accurately simulate the complex reflectance patterns of materials at fine scales, going beyond current parametric models. The neural...
- The University of California, San Diego will receive $800,000 from the National Science Foundation under the agency's Computer and Information Science and Engineering program (CFDA 47.070) to conduct collaborative research titled "Differentiable Rendering for Computer Graphics" from July 2021 through June 2025. The project aims to advance the development of differentiable rendering techniques, which allow gradients of images to be backpropagated through the entire rendering process....
- The University of California, San Diego will use a $500,000 project grant from the National Science Foundation to support research titled "SMALL: PHYSICALLY-BASED LEARNING FOR SHAPE, LIGHTING AND MATERIAL IN COMPLEX INDOOR SCENES" from October 1, 2021 through September 30, 2024. The grant is funded through the NSF's Computer and Information Science and Engineering program (CFDA #47.070), which supports investigator-initiated research and education in computing, communications, and...
- This National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) project grant (CFDA 47.070) provides $600,000 in funding to the University of California, San Diego (UCSD) from July 2024 to June 2027. The project aims to develop a novel, resolution-independent neural image representation that preserves key image discontinuities, enabling higher-fidelity computer graphics and computational photography applications. Key deliverables include a 2D...
- The National Science Foundation Division of Computing and Communication Foundations awarded the College of William & Mary $600,000 on October 1, 2026, under the Computer and Information Science and Engineering program (CFDA 47.070) to develop an AI-enhanced framework for authoring digital material representations from ordinary photographs. The research will investigate learned material-to-material (MAT2MAT) transformations that convert one digital material representation into another,...
- The National Science Foundation (NSF) Division of Information and Intelligent Systems awarded a $600,000 Project Grant to the University of California, San Diego (UCSD) under the Computer and Information Science and Engineering (CFDA 47.070) program. The 3-year grant, effective July 1, 2023, supports research to develop dynamic neural network architectures that can efficiently enable multimodal perception, including vision, audio, and language processing. The research aims to address...
- The National Science Foundation Division of Computing and Communication Foundations awarded the University of California, San Diego $600,000 on July 1, 2026, under the Computer and Information Science and Engineering program (CFDA 47.070) to develop selective prediction techniques for visual-language models that can detect and avoid hallucinations. The project develops methods enabling large visual-language models to recognize uncertainty and abstain from making unreliable predictions in...
- This $600,000 project grant, awarded by the National Science Foundation (NSF) under the Computer and Information Science and Engineering (CFDA 47.070) program, will support research to develop a new Bayesian diffusion model framework for advanced visual perception and cognition systems. The University of California, San Diego (UCSD) will serve as the primary awardee, with the goal of revisiting the analysis-by-synthesis methodology by integrating generative priors into the learning and inference...
- The National Science Foundation Division of Information and Intelligent Systems awarded $412,579 to the University of California Irvine on January 15, 2026, under the Computer and Information Science and Engineering program (CFDA 47.070) to develop vision systems that can adapt and generalize across changing visual domains and environmental conditions. The award funds research into model design and learning approaches for multi-domain generalization that facilitate future adaptation,...
The National Science Foundation Division of Computing and Communication Foundations awarded the University of California, San Diego $300,000 on October 1, 2026, under the Computer and Information Science and Engineering program (CFDA 47.070) to develop a machine-learning framework for neural light transport and material representation in computer graphics rendering. The project will create a unified machine-learning approach to learn how objects reflect light from real and simulated measurements, enabling realistic image synthesis with reduced model complexity. The work targets two primary deliverables: direct prediction of light reflection through scenes without explicit simulation, and generative AI tools that automatically create fine-scale scene detail from coarse models, text, and images. The framework is designed to support downstream applications in industrial design, entertainment, advertising, home remodeling, and architecture. The project also includes curriculum development to reflect machine learning's impact on computer graphics education. Work is performed in La Jolla, California through September 30, 2029.
Mod # | Description | ReasonForModification | Federal Obligation | Date |
|---|---|---|---|---|
| Not listed | $300.0k | 7/26/26 |