This $1,200,000 Project Grant awarded by the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) supports the development of a new class of digital shape models capable of accurately representing deformable objects like animal bodies and human hands, even when their internal skeletal structures deviate from the norm. The research will create a universal deformable shape modeling framework that integrates data from 3D scans, images, and videos to handle objects with varied skeletal topologies. Key products include novel methods for keypoint detection, skeletal graph inference, and multimodal shape alignment, enabling robust reconstruction of deformable structures from visual cues. This work has the potential to advance research in biology, medicine, and education by supporting flexible modeling across a broad spectrum of species and conditions. The award was granted to the University of Texas at Austin and runs from July 1, 2025 to June 30, 2029.
Mod # | Description | Reason For Modification | Federal Obligation (Click to sort descending) | Date (Click to sort ascending) |
|---|---|---|---|---|
| Not listed | $1.2m | 6/23/25 |