Students

Dakshit Agrawal

Dakshit is pursuing his Master’s in Computer Vision at Carnegie Mellon University (CMU) and is expected to graduate in May 2023. He completed his Bachelor in Technology from the Indian Insitute of Technology Roorkee (IIT Roorkee), after which he worked for 1.5 years at Rephrase.ai, helping generate studio-quality talking head videos from any text. He also has worked with Prof. Marco Pedersoli and Prof. Jose Dolz at ETS Montreal, Prof. Venkatesh Babu at the Indian Insitute of Science Bengaluru, and Prof. Katerina Fragkiadaki at CMU, publishing in notable conference venues like ICMI 2018 and ICCV 2019.

Jiajie Xu

Jiajie is a Master of Science in Computer Vision student at Carnegie Mellon University and is expected to graduate in May 2023. He completed his Bachelor of Applied Science Degree at University of Toronto, during which he worked with Prof. Jessica Burgner-Kahrs on continuum robotics. He has a broad research interest of computer vision in AR, autonomous driving, and robotics. He has previously interned at Meta Reality Labs, SenseTime, and Epson.

Advisors

Prof. Ioannis Gkioulekas

Prof. Gkioulekas is an Assistant Professor in the Robotics Institute at Carnegie Mellon University. He received his PhD from the School of Engineering and Applied Sciences at Harvard University, where his advisor was Todd Zickler. Before that, he received a Diploma (five-year degree) in Electrical and Computer Engineering from the National Technical University of Athens, where he worked with Petros Maragos.
His research interest is mainly on computational imaging, which can be broadly described as coming up with systems that combine imaging (optics, sensors, illumination) and computation (physics-based modeling and rendering, inverse algorithms, learning) in innovative, unexpected, and meaningful ways.

Dr. Ashish Shrivastava

Dr. Shrivastava is a tech lead on utilizing the synthetic data for ML at Cruise. Prior to this, he was a Researcher and tech lead at AI Research, Apple where his focus was on advancing autonomous technologies and continuously improving machine learning research at Apple. He developed machine learning algorithms with a focus on long term impact on the project, and developed core research technologies that influenced multiple groups at Apple as well as advanced the state-of-the-art in machine learning. His research has been presented in many Apple tech talks at top AI conferences like CVPR, NIPS, as well as receiving the CVPR2017 best paper award. Before joining Apple, he was a Senior Research Engineer who laid the foundation for Appearance Search technology at Avigilon that develops innovative high-definition surveillance systems.
He completed his PhD working with Prof. Rama Chellappa at University of Maryland, College Park. During his PhD, he worked on a variety of computer vision and machine learning algorithms such as sparse representation, dictionary learning, object recognition, multiple instance learning, multi-modal fusion, etc.

Dr. Siva Karthik Mustikovela

Dr. Mustikovela is a researcher working on problems pertaining to perception / computer vision at Cruise. He is interested in creating algorithms and data for semi and self-supervised learning problems.
During his PhD at Heidelberg University, he worked on computer vision problems like stereo and flow estimation, object detection, semantic segmentation, object pose estimation using Deep Learning/ Convolutional Neural Network models.

Dr. Yuning Chai

Dr. Chai is the Head Of AI Research at Cruise, building out its applied research organization. Prior to this, he was the staff research lead and manager for perception and prediction at Waymo, and a research scientist at Google.
He completed his PhD in computer science at University of Oxford, Visual Geometry Group, focusing on fine-grained visual categorization (FGVC).