Light Field
Light fields are four-dimensional representations of light rays capturing both spatial and angular information, enabling advanced imaging and rendering capabilities. Current research focuses on improving light field acquisition efficiency, enhancing resolution through techniques like super-resolution and neural networks (including transformers and diffusion models), and developing efficient compression methods using implicit neural representations. These advancements are driving progress in diverse applications, including microscopy, underwater imaging, 3D display technology, and novel view synthesis for virtual and augmented reality.
Papers
Generative deep learning-enabled ultra-large field-of-view lens-free imaging
Ronald B. Liu, Zhe Liu, Max G. A. Wolf, Krishna P. Purohit, Gregor Fritz, Yi Feng, Carsten G. Hansen, Pierre O. Bagnaninchi, Xavier Casadevall i Solvas, Yunjie Yang
Time-Efficient Light-Field Acquisition Using Coded Aperture and Events
Shuji Habuchi, Keita Takahashi, Chihiro Tsutake, Toshiaki Fujii, Hajime Nagahara