top of page
  • gscholar
  • LinkedIn

Machine Intelligence & Data Science
(MIDAS) Laboratory

We are developing state-of-the-art AI & data science solutions for computational imaging and vision, as well as improving their fundamental understanding.

ds_edited_edited.jpg

Research Overview

Our research interests in data science include

  • AI & machine learning,

  • optimization, and 

  • sampling

with past and current projects in computational imaging and vision:

  • computational photography,

  • medical imaging, and

  • vision-based autonomous systems.

Latest Publications

Diffusion models for three-dimensional (3D) volume reconstruction

Diffusion models can generate high-quality and diverse samples. By changing additional information so-called condition and conditional approach, one can manipulate generation outcomes. The paper proposes a new conditional diffusion model that reconstructs high-quality 3D volumes from a few 2D images with a new vision transformer architecture.

bottom of page