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 Project Grant award, provided by the National Science Foundation (NSF) under the Computer and Information Science and Engineering (CFDA 47.070) program, focuses on advancing the field of robotic visual perception by addressing limitations in current artificial intelligence systems. The $174,604 award, effective June 15, 2025 through May 31, 2027, aims to develop novel frameworks for understanding human behaviors and interactions, and creating robust learning mechanisms from sparse data. Key...
This Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program, CFDA 47.070, supports a research project titled "CAREER: ACTIVE SCENE UNDERSTANDING BY AND FOR ROBOT MANIPULATION" at Stanford University. The $130,000 grant, awarded on October 1, 2023, aims to develop a self-improving robot perception system that leverages manipulation skills for active scene understanding. The key focus is on enabling robots to...
This $341,618 Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) aims to develop a new computational framework for understanding human behavior and activities in 4D (3D over time) from video. The project will create a scalable, transformer-based model that integrates the 4D state of humans with their surrounding environments, social interactions, and object use. This approach accommodates various video...
This $400,000 project grant awarded by the National Science Foundation (NSF) under the Computer and Information Science and Engineering (CFDA 47.070) program supports research to develop a systematic framework for visualizing, understanding, and rewriting the learned computations of multimodal generative AI models. The key objectives are to: 1) create new methodologies to visualize the internal mechanisms and hierarchical structures of pre-trained multimodal generative models, 2) explore model...
This National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) Federal Grant Program (CFDA 47.070) award to Clemson University will develop a 3D computer vision framework that fuses multiple sensing modalities to enhance feature extraction, tracking, and large-scale scene reconstruction in unstructured environments. The $599,945 project, awarded on June 15, 2025, aims to improve perception accuracy and adaptability for autonomous navigation, environmental...
The National Science Foundation (NSF) has awarded a $600,000 five-year Project Grant under its Computer and Information Science and Engineering (CFDA 47.070) program to the University of California, San Diego (UCSD) to conduct research on "Interaction-Oriented 3D Representation Learning on Point Cloud". The research aims to develop novel deep learning frameworks that can learn 3D representations from point cloud data and leverage these representations to optimally plan and execute...
This NSF Computer and Information Science and Engineering (CISE) Program (CFDA 47.070) Project Grant, awarded to Arizona State University in the amount of $598,123 on July 15, 2024, will develop new algorithms to enable AI systems to autonomously learn hierarchical world models and high-level actions. The goal is to create AI systems, such as hospital robots and disaster-recovery support systems, that can plan reliably and efficiently to accomplish complex user-desired tasks, without requiring...
This Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) provides $299,964 to enhance how computers perceive and recognize shapes in images and 3D data. The project aims to develop deep learning techniques that enable computers to focus on the critical parts of an object, disregarding background distractions, and comprehend the relationships between different object parts. This work could advance...
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...