This Project Grant award, funded by the National Science Foundation (NSF) under the Computer and Information Science and Engineering (CFDA 47.070) program, aims to develop a hybrid, vision-centric framework that integrates intuitive and deliberate visual processing to create more robust visual intelligence. The $111,878 award to New York University (NYU) supports research focused on three primary directions: 1) advancing vision-centric parametric knowledge through techniques like visual...
The National Science Foundation (NSF) awarded a Project Grant of $599,649 to Carnegie Mellon University (CMU) under the Computer and Information Science and Engineering (CFDA 47.070) program. The goal of this 3-year project, which commenced on April 15, 2024, is to develop perception systems that can infer the 3D structure of generic objects or scenes from 2D images, even with partial observations. Key technical efforts will include formulating mechanisms for learning novel 3D generative...
This four-year, $400,000 Project Grant from the National Science Foundation's Division of Information and Intelligent Systems supports research at the Massachusetts Institute of Technology under the Computer and Information Science and Engineering program. The grant funds the development of new techniques for composing implicit representations to enable machines to perceive and reconstruct 3D scenes in a more generalizable manner. Investigators will explore methods to make representations...
This National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) Federal Grant Program (CFDA 47.070) award provides $348,956 to Carnegie Mellon University (CMU) to develop computational systems that can perceive and understand the 3D structure and actionable affordances of the physical world. The 5-year project aims to bridge the gap between computer vision systems and human-level understanding of 3D scenes and the effects of actions within them. Key research...
This $600,000 Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) supports research at the University of California, San Diego (UCSD) to develop theoretical frameworks and computational methods for reconstructing complex 3D shapes using neural implicit representations. The key objectives are to enable the reconstruction of 3D shapes with intricate topologies, such as objects with holes, and to allow...
This $599,945 project grant award from the National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) will fund research at Clemson University to develop advanced 3D computer vision capabilities for unstructured environment exploration. The project aims to create a framework that integrates multi-modal sensing, feature extraction, and dynamic scene reconstruction to enable robust 3D visual representation in complex, unpredictable environments....
This National Science Foundation (NSF) Division of Information and Intelligent Systems (CFDA #47.070) $1,034,326 Project Grant awarded to Brown University supports collaborative research to bridge the semantic-metric gap in multinocular 3D vision systems. The project aims to address key technical challenges in 3D computer vision, such as handling blurry/textureless images, leveraging redundant image data, and connecting geometric point clouds to semantic scene representations. The research...
This Project Grant award, funded by the National Science Foundation (NSF) under the Computer and Information Science and Engineering (CFDA 47.070) program, focuses on advancing robotic visual perception and human-like visual understanding. The project, entitled "CRII:RI: ADVANCING HUMAN-EMBODIED VISUAL RECOGNITION," aims to address limitations in current artificial intelligence systems by developing novel frameworks for understanding human behaviors and interactions, as well as...
This $499,999 federal Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) will support collaborative research to investigate the theoretical foundations of compositional learning in large language models (LLMs) based on transformer architectures. The research aims to advance the understanding of how LLMs, such as GPT-4, LLAMA 2, and CLAUDE 3, can decompose complex tasks into simpler intermediate steps to...
Rice University was awarded a $499,760 Project Grant from the National Science Foundation Division of Information and Intelligent Systems on October 1, 2021 to support research titled "CAREER: TEACHING MACHINES TO RECOGNIZE COMPLEX VISUAL CONCEPTS IN IMAGES THROUGH COMPOSITIONALITY." The grant is being administered through the NSF's Computer and Information Science and Engineering program (CFDA #47.070), which supports investigator-initiated research and education in all areas of...
This Project Grant award of $450,626.00 from the National Science Foundation (NSF) Computer and Information Science and Engineering (CFDA 47.070) program supports research to develop a computer vision framework that learns and understands the physical world in a compositional manner. The key products and services to be delivered include:
Establishing a unified framework for representing, parsing, and learning the compositionality of physical objects through disentangled modeling of large shape variations, constituent parts, and detailed deformations.
Developing a new compositional model that parses 3D dynamic scenes from streaming video into an explainable layout graph, by constructing distributed representations of low-level geometry and motion and performing explicit reasoning about high-level scene compositionality.
Extending the first two thrusts by modeling the compositionality of generic articulated objects and investigating test-time adaptation for 3D dynamic scene parsing.
This research aims to advance fundamental understanding of visual compositionality, physical object and scene understanding, and explainable parsing, with potential impacts on applications like robotics, autonomous vehicles, and augmented reality. The award period is from July 1, 2025 to June 30, 2030.