Menu
Explore a research direction
Computer vision
research labs.
Discover research in computer vision, image processing, and visual computing through faculty-led lab profiles. Review publications and official sources to understand each group's specific focus.
What to compare
Compare the kinds of visual data and problems a group studies. Look for differences between image analysis, video, three-dimensional scenes, and domain-specific applications, and ask how results are evaluated.
Profiles appear here because their listed research keywords match this topic. Inclusion does not establish an open position. Check the official sources and any published application instructions before reaching out.
Prepare a research introduction ↗45 research-led lab profiles
Browse labs by their listed college affiliationKaiming He Research Group
Massachusetts Institute of TechnologyKaiming He · Associate Professor
How can deep learning methods give computers the ability to perceive and recognize the visual world? Kaiming He is best known for his work on Deep Residual Networks, whose residual connections are now used in modern deep learning models, including Transformers, AlphaGo Zero, and AlphaFold. He is also known for his work on visual perception, including Faster R-CNN and Mask R-CNN, which appear among his selected publications. His work on self-supervised learning includes Momentum Contrast and Masked Autoencoders, which are also listed among his selected publications. Recent publications cover generative modeling, including Mean Flows for one-step generative modeling, letting denoising generative models denoise, and autoregressive image generation without vector quantization.
Kate Saenko Research Group
Boston UniversityKate Saenko · Professor
How can machines learn to understand vision and language? Kate Saenko directs the Computer Vision and Learning Group and is a member of the IVC Group. Her research interests are in the broad area of Artificial Intelligence. The focus is on Adaptive Machine Learning, Learning for Vision and Language Understanding, and Deep Learning. She received her PhD from MIT and was previously a Postdoctoral Researcher at the International Computer Science Institute.
Kavita Bala Research Group
Cornell UniversityKavita Bala · Provost Professor of Computer Science
How can visual systems identify materials and lighting from photographs to enable realistic editing and recognition? The group develops datasets and algorithms for material recognition and visual search, including the Materials in Context Database and visual similarity models. Researchers build physically-based and differentiable rendering methods for recovering shape and material properties to support editing and relighting. The group applies remote-sensing and scale-aware recognition techniques to satellite imagery and cloud removal benchmarks for Earth-observation tasks. Methods combine convolutional neural networks, differentiable Monte Carlo rendering, and dataset/benchmark construction to evaluate recognition and inverse-rendering performance.
Kilian Weinberger Research Group
Cornell UniversityKilian Weinberger · Professor
How can machine learning systems work well and be applied across many different problem areas? Kilian Weinberger is a Professor in the Department of Computer Science at Cornell University. He received his Ph.D. from the University of Pennsylvania in Machine Learning under the supervision of Lawrence Saul. He has worked on computer vision, autonomous vehicles, Gaussian Processes, and deep learning. He has also worked on metric learning and AI in Science, alongside his work on learning under resource constraints.
Louis-Philippe Morency Research Group
Carnegie Mellon UniversityLouis-Philippe Morency · Leonardo Associate Professor of Computer Science
How can computers analyze, recognize and predict subtle human communicative behaviors during social interactions? Louis-Philippe Morency is a Leonardo Associate Professor of Computer Science in the Language Technology Institute at Carnegie Mellon University. He directs the MultiComp Lab, the Multimodal Communication and Machine Learning Laboratory. His research centers on multimodal machine learning, a mathematical foundation to study heterogeneous multimodal data and the contingency often found between modalities. His page also lists health behavior informatics, with technologies to support clinical practice during diagnosis and treatment of mental health disorders.
Martial Hebert Research Group
Carnegie Mellon UniversityMartial Hebert · Dean and University Professor of Robotics
How can autonomous systems detect, track and predict in dynamic environments? Martial Hebert is Dean and University Professor of Robotics in the School of Computer Science. His research statement lists efficient techniques for object and category recognition. It also lists the use of contextual information, in particular 3-D geometry from images, for scene analysis. His research topics include computer vision, intelligent transportation systems, sensing & perception, and field & service robotics.
Mert Rory Sabuncu Research Group
Cornell UniversityMert Rory Sabuncu · Professor of Electrical and Computer Engineering
How can artificial intelligence improve medical imaging? Mert Sabuncu is the Andrew H. & Ann R. Tisch Professor at Cornell Tech. The AI for Medical Imaging initiative spans Cornell Tech and Weill Cornell Medicine Radiology. He is also Vice Chair of AI and Engineering Research in the Department of Radiology at Weill Cornell Medicine. He is a co-founder and executive editor of MELBA, The Journal of Machine Learning for Biomedical Imaging.
Nan-kuei Chen Research Group
University of ArizonaNan-kuei Chen · Professor of Biomedical Engineering
How can MRI acquisition and reconstruction be improved to deliver high-resolution, artifact-free scans for challenging patients within clinical time limits? The research develops novel acquisition and reconstruction approaches, including multiplexed sensitivity encoded (MUSE) MRI, to map human brain connectivity at high spatial resolution. Projects focus on artifact characterization and correction for EPI distortions, susceptibility-induced signal loss, Nyquist and motion-induced phase errors using pulse sequence design and signal processing. Researchers combine fast image acquisition, denoising, and algorithm development to enable multi-contrast and quantitative MRI in clinically-feasible timeframes. The lab implements and validates methods through applied studies, NIH-funded projects, and collaborations on diffusion and functional MRI.
Noah Snavely Research Group
Cornell UniversityNoah Snavely · Professor of Computer Science
How can computers understand and depict three-dimensional scenes from images? Noah Snavely is a Professor of Computer Science at Cornell Tech interested in computer vision and computer graphics. His research interests are in computer vision and graphics, in particular in 3D understanding and depiction of scenes from images. He is a member of the Cornell Graphics and Vision Group. Selected projects listed on his page include ZipMap, MegaSaM and Stereo4D.
Noorbakhsh Amiri Golilarz Research Group
The University of AlabamaNoorbakhsh Amiri Golilarz · Assistant Professor
Noorbakhsh Amiri Golilarz's faculty-led research profile covers Artificial Intelligence, Computer Vision, Data Analytics, and Deep Learning.
Pedro F. Felzenszwalb Research Group
Brown UniversityPedro F. Felzenszwalb · Professor of Engineering and Computer Science
How can algorithms detect and localize people and objects robustly in natural images with deformations and occlusions? The lab developed and evaluated a deformable part model for person detection in benchmark challenges to improve object localization under variation. Researchers design and analyze algorithms connecting computer vision with optimization and statistics to enable reliable image restoration and segmentation. The group implements method combinations from machine learning, signal processing and natural language processing to address mid- and high-level vision tasks. The team releases papers, talk slides and code to document methods and reproducible evaluations.
Pedro Felipe Felzenszwalb Research Group
Brown UniversityPedro Felipe Felzenszwalb · Professor of Engineering and Computer Science
How can ideas from artificial intelligence and optimization help computers solve problems in computer vision? Pedro Felipe Felzenszwalb's main research interests are in computer vision, artificial intelligence, machine learning, optimization and signal processing. He has worked on a range of problems within computer vision, including the problem of image restoration. He has also worked on the problem of image segmentation and the problem of object recognition. His research connects computer vision and artificial intelligence to areas including optimization, statistics, and natural language processing.
Phillip Isola Research Group
Massachusetts Institute of TechnologyPhillip Isola · associate professor
To what extent do different AI models, trained on different data and modalities, learn similar representations of the world? The group led by Phillip Isola aims to understand the fundamental principles of intelligence. One research direction characterizes how models represent the world in terms of the geometric structures of their representations. A second direction studies AI agents as an ethologist would, documenting and trying to understand their behavior. Representative projects include The Platonic Representation Hypothesis and a study titled Is This Machine Playing?
Ramin Zabih Research Group
Cornell UniversityRamin Zabih · Professor of Computer Science
When can a generative model that produces convincing video be trusted to answer what if questions? Ramin Zabih is a Professor of Computer Science at Cornell University and Cornell Tech. His research interests have always been in computer vision, and his main focus now is bringing techniques from causal inference into it. The group studies counterfactual world models, generative models asked what would happen under a different action instead of what usually happens next. Three questions organize the work: diagnosing which action-situation pairs the model is hallucinating, fixing them by reweighting training, and certifying the result.
Regina Barzilay Research Group
Massachusetts Institute of TechnologyRegina Barzilay · School of Engineering Distinguished Professor for AI and Health
Can machine learning detect cancer risk from routine clinical imaging before symptoms appear to enable earlier intervention? The group develops deep-learning models for personalized mammography-based risk prediction and early cancer detection. Researchers build ML methods for de-novo molecular design and retrosynthesis to change traditional drug-discovery pipelines toward data-driven generation. The team develops generative models such as BoltzGen to create protein binders for biological targets and tools like VaxSeer to predict virus evolution for vaccine strain selection. They also focus on interpretability and robustness for clinical AI to support safer, fairer deployment in healthcare settings.
Ryan Carney Research Group
University of South FloridaRyan Carney · Associate Professor
Dinosaurs and disease surveillance meet in Ryan Carney’s unusually broad research program. His paleontology work uses three-dimensional imaging, modeling, and animation to study Archaeopteryx, functional anatomy, and the evolution of bird flight. A second direction applies artificial intelligence, citizen-science observations, remote sensing, and geographic modeling to mosquitoes and the diseases they transmit. Virtual and augmented reality help translate anatomical research into visual teaching tools. Across these projects, digital methods reveal biological patterns and make complex information useful for scientific analysis, education, and public-health monitoring.
Sudeep Sarkar Research Group
University of South FloridaSudeep Sarkar · Distinguished University Professor
Sudeep Sarkar studies how computers can understand the content and activity in images and video. His research covers visual grouping, gait biometrics, action recognition, medical images, and economic signals visible in satellite imagery. A major direction combines symbolic representations with deep learning to interpret events and support activities of daily living, including assistive robotics. The work links foundational computer vision with applications across medicine, engineering, and independent living. It is relevant to researchers interested in AI systems that reason about visual scenes and changing human activities.
William T. Freeman Research Group
Massachusetts Institute of TechnologyWilliam T. Freeman · Thomas and Gerd Perkins Professor of Electrical Engineering and Computer Science
How can computers learn to interpret images, audio, and photographs of the world the way people do? William T. Freeman is interested in mid-level vision, audio, and computational photography. Previous research topics include steerable filters and pyramids, orientation histograms, and the generic viewpoint assumption. Earlier work also covered motion magnification, which reveals tiny movements in video, and belief propagation in networks with loops. Other past topics include color constancy and computer vision for computer games.
Xiaohui Xie Research Group
University of California, IrvineXiaohui Xie · Professor of Computer Science
How can AI and machine learning help tackle critical challenges in biology and medicine? Professor Xie's research interests include AI/Machine Learning, Bioinformatics, and Computer Vision. His listed research areas include AI, ML and Natural Language Processing. Another listed area is Biomedical Informatics and Computational Biology, which uses techniques from applied mathematics, informatics, statistics and computer science to solve biological problems. A third listed area is Computer Graphics and Vision, which covers generating, capturing, representing, rendering and interacting with synthetic and real-world images and video.
Yu-Wing Tai Research Group
Dartmouth CollegeYu-Wing Tai · Associate Professor
How can computer vision and machine learning be applied to low-level vision, image and video editing, and segmentation? The major research interests of Yu-Wing Tai are in the broad areas of computer vision and machine learning. These areas include low-level vision, image and video editing, segmentation, 3D reconstruction, human pose estimation and video analysis. Tai is also interested in AIGC, multimodalities, and large generative pre-trained models and their applications. The directory lists deep learning among his areas of expertise, alongside computer vision and machine learning.
Yuyin Zhou Research Group
University of California, Santa CruzYuyin Zhou · an Assistant Professor in Computer Science and Engineering at UC Santa Cruz
What does research on AI for healthcare, medical image computing, computer vision and machine learning involve? Yuyin Zhou is an Assistant Professor in Computer Science and Engineering at UC Santa Cruz. Her primary focus is AI for healthcare, medical image computing, computer vision, and machine learning. She has organized workshops, competitions and tutorials at major conferences including ICML, MICCAI and ML4H. She serves as a regular Area Chair for CVPR, ECCV, ICLR and MICCAI.
Showing 25–45 of 45 labs