Visual Computing and Computational Imaging

The computer science visual computing research area focuses on developing computational algorithms and machine learning frameworks to address complex challenges in the visual domain.

Research Focus

  • Computer Vision: Designing algorithms to extract meaningful information from images, video, and 3D scans: e.g., object recognition, scene understanding, 3D reconstruction, generative modeling, vision and language, theoretical foundations of visual deep learning, remote sensing, 3D vision, video understanding, and segmentation.
  • Computer Graphics: Developing techniques for image generation and the processing of 3D shapes and scenes: e.g., geometry processing, computational design, physically-based simulation, and procedural modeling.
  • Computational Imaging and Display: hardware-software co-design of cameras and display devices, including end-to-end optical design, differentiable optical simulation, and applications to both consumer devices and scientific imaging problems.
  • Scientific Visualization: Developing techniques to visually represent and explore complex scientific data for enhanced analysis and understanding: e.g. nano visualization, visualization of tensor fields, visualization and modeling of biological systems, and large-scale visualization.
  • Human-Computer Interaction (HCI): Investigating the intersection of human perception, cognition, and visual interfaces for user-friendly and intuitive systems.
  • Interdisciplinary Applications: Developing applications of computer vision, computer graphics, and visualization in conjunction with domain sciences: e.g., mechanical engineering, physics, solar energy, biology, biomedical imaging, robotics, and geosciences.