Eric Smith joined Kitware in 2011 and is a Principal Engineer on the Computer Vision Team. He holds a Ph.D. in computer vision from Rensselaer Polytechnic Institute, where he also received his B.S. in computer science.

Dr. Smith’s research at Kitware has largely focused on image enhancement and 3D reconstruction. He is currently leading image enhancement projects for both underwater (DARPA) and overhead (NGA) domains. He is a key contributor to Kitware’s 3D reconstruction application, Telesculptor. Dr. Smith recently led an effort on aerial 3D reconstruction (AFRL) contributing depth map estimation and fusion to Telesculptor. His recent research at Kitware has included deep learning for estimating depth maps, super-resolution, modality transfer, semantic segmentation, and object detection. He has previously worked on variational algorithms for both dense depth estimation and super-resolution from video, as well as camera trajectory tracking of an endoscope.

Dr. Smith’s graduate research focused on the automatic registration of combined image/LiDAR scans. He developed a pairwise registration algorithm designed to handle scan pairs suffering from low overlap, changes, intensity differences, and wide viewpoint differences. Dr. Smith has also worked on feature detection, description, and matching algorithms targeted at coarse alignment for combined image/LiDAR scans. He has also developed a fully automatic multiple scan registration algorithm using both pairwise and graph-based validation methods.