Richard Szeliski

Richard Szeliski
Name	Richard Szeliski
Fields	Computer vision, Computer graphics, Image processing
Workplaces	Microsoft Research, New York University, University of Southern California
Alma mater	Princeton University, Massachusetts Institute of Technology
Known for	Image-based modeling, Photogrammetry, Computer vision textbooks

Richard Szeliski is a researcher and author known for contributions to computer vision, computer graphics, and image processing. He has held positions in academia and industry, authored a widely used textbook, and led research groups at prominent institutions. His work spans image-based rendering, structure from motion, and practical systems for visual computing.

Early life and education

Szeliski studied at institutions including Princeton University and Massachusetts Institute of Technology where he engaged with faculty and researchers linked to SIGGRAPH, IEEE Computer Society, and Association for Computing Machinery. His doctoral work connected him to research groups associated with Stanford University and Carnegie Mellon University, situating him among contemporaries who later joined Microsoft Research, Google, and Adobe Systems. During his formative years he interacted with projects related to ImageNet, Brown University collaborations, and conferences like CVPR and ICCV.

Research and contributions

Szeliski's research includes image-based modeling, structure from motion, and patch-based synthesis, influencing systems developed at Microsoft, Google Research, and Facebook AI Research. He advanced techniques used in photogrammetry, 3D reconstruction, and dense stereo matching, connecting to work from University of Oxford, ETH Zurich, and Max Planck Society. His algorithms intersect with methods from Lucas–Kanade, Horn–Schunck, and variational approaches discussed at NeurIPS, ECCV, and SIGGRAPH Asia. Contributions influenced projects like Photosynth, Microsoft Kinect, Street View, and tools by Autodesk, Pixar, and Weta Digital.

Career and industry roles

Szeliski served as a researcher and leader at Microsoft Research where he collaborated with groups across Redmond, Cambridge (UK), and Silicon Valley. He was affiliated as faculty with New York University and University of Southern California, engaging with centers such as NYU Tandon School of Engineering and labs collaborating with DARPA and NSF. His career overlapped with engineers and scientists from Apple, Amazon, NVIDIA, and Intel on visual computing initiatives. He contributed to community efforts tied to SIGGRAPH, ICML, AAAI, and editorial boards of venues like IEEE Transactions on Pattern Analysis and Machine Intelligence.

Awards and recognitions

Szeliski received recognitions from organizations including ACM, IEEE, and conference awards from CVPR and SIGGRAPH. His textbook and survey articles have been cited in awards given by Royal Society-associated workshops and prizes with committees drawing from National Academy of Engineering-affiliated reviewers. He has been invited to give keynote lectures at events such as SIGGRAPH, ECCV, and ICCV and received fellowships and honors connected to NSF and industrial research awards from Microsoft and Adobe Research.

Selected publications and books

Szeliski authored a comprehensive textbook on visual computing frequently cited alongside works by Richard Hartley, Andrew Zisserman, David Forsyth, Jean Ponce, and Takeo Kanade. His publications appeared in proceedings of SIGGRAPH, CVPR, ICCV, ECCV, and journals such as IEEE Transactions on Pattern Analysis and Machine Intelligence and International Journal of Computer Vision. Notable topics include multi-view stereo, panorama stitching, image mosaicing, and photometric stereo, relating to research by Marc Pollefeys, Matthew Brown, Richard Szeliski (do not link), Noam Snavely, and Sameer Agarwal.

Teaching and mentorship

In academic roles at institutions like New York University and University of Southern California, Szeliski supervised students who later joined organizations including Google Research, Facebook AI Research, Apple, and NVIDIA. His teaching covered material overlapping with courses taught by faculty at MIT, Stanford University, UC Berkeley, and Princeton University, and he participated in summer schools and workshops organized by CVPR and SIGGRAPH.

Category:Computer scientists Category:Computer vision researchers