A native of France, Martial Hebert earned a doctorate in computer science at the University of Paris. He joined the Robotics Institute in 1984 — just five years after it was founded — and was named a full professor in 1999. Upon joining the CMU faculty, Hebert became part of the Autonomous Land Vehicles program, a precursor of today's research on self-driving vehicles. He performed research on interpreting 3D data from range sensors for obstacle detection, environment modeling and object recognition. For the next three decades, he led major research programs in autonomous systems, including ground and air vehicles, with contributions in the areas of perception for environment understanding and human interaction.
Hebert's research primarily centers on computer vision. He has led research on fundamental components, such as scene understanding, object recognition and applying machine learning to computer vision, as well as applications, which include systems that enable older adults and people with disabilities to live more independently. To help meet the needs of a rapidly expanding computer vision industry, he created the nation's first master's degree program in computer vision.
As director of the Robotics Institute, Hebert led an institution with more than 800 community members, including faculty, students and staff and colleagues at the National Robotics Engineering Center. During his tenure, the institute's operating budget reached an all-time high.
Hebert is a member of both the IEEE Robotics and Automation, and the IEEE Computer societies. Throughout his career, he has published hundreds of refereed papers in journals and conference proceedings, and has contributed to multiple edited volumes. He currently serves as editor-in-chief of the International Journal of Computer Vision. In 2022 he was named a University Professor, CMU's highest distinction for faculty members.
Areas of Expertise (5)
Robotics and Autonomous Vehicles
Interpretation of Perception Data
Media Appearances (5)
Computer vision researchers use motion to discover objects in videos
Tech Xplore online
Martial Hebert, dean of CMU's School of Computer Science and a professor in the Robotics Institute, and robotics Ph.D. student Zhipeng Bao collaborated on the project with Toyota Research Institute, which sponsored the work. The research could help computers and robots better automatically detect objects in videos.
Back to the future: Look to the 1980s for guidance on AI management
The Hill online
Many have called to slow down the advancement of large language models, the kind of artificial intelligence (AI) that powers ChatGPT. But when it comes to AI development, we need to act now.
Hebert, Hooker and Kraut Named University Professors
Carnegie Mellon University News online
Three Carnegie Mellon University faculty members have been elevated to the rank of University Professor(opens in new window), the highest distinction a faculty member can achieve at CMU. The newly appointed University Professors are Martial Hebert, John Hooker and Robert E. Kraut.
Hebert Installed as SCS Dean
Carnegie Mellon University News online
It's fitting that the installation of School of Computer Science Dean Martial Hebert would begin with a musical intro from Carnegie Mellon University's robot bagpiper, McBlare. After all, Hebert spent his career at the Robotics Institute until taking the helm of SCS this past August.
CMU names Martial Hebert Dean of School of Computer Science
The Robot Report online
Martial Hebert, a leading researcher in computer vision and robotics, has been named dean of Carnegie Mellon University’s world-renowned School of Computer Science (SCS), effective August 15.
Industry Expertise (3)
University of Paris: Doctorate, Computer Science
University of Paris: Maitrise de Mathématiques Appliquées
University of Paris: License de Mathématiques
- IEEE Robotics and Automation Society : Member
- IEEE Computer Society : Member
- International Journal of Computer Vision : Editor-in-Chief
Object Discovery From Motion-Guided TokensProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
2023 Object discovery -- separating objects from the background without manual labels -- is a fundamental open challenge in computer vision. Previous methods struggle to go beyond clustering of low-level cues, whether handcrafted (e.g., color, texture) or learned (e.g., from auto-encoders). In this work, we augment the auto-encoder representation learning framework with two key components: motion-guidance and mid-level feature tokenization.
Learning Continuous Implicit Representation for Near-Periodic PatternsEuropean Conference on Computer Vision
2022 Near-Periodic Patterns (NPP) are ubiquitous in man-made scenes and are composed of tiled motifs with appearance differences caused by lighting, defects, or design elements. A good NPP representation is useful for many applications including image completion, segmentation, and geometric remapping.
Approximate Differentiable Rendering with Algebraic SurfacesEuropean Conference on Computer Vision
2022 Differentiable renderers provide a direct mathematical link between an object’s 3D representation and images of that object. In this work, we develop an approximate differentiable renderer for a compact, interpretable representation, which we call Fuzzy Metaballs. Our approximate renderer focuses on rendering shapes via depth maps and silhouettes. It sacrifices fidelity for utility, producing fast runtimes and high-quality gradient information that can be used to solve vision tasks.
Semantically supervised appearance decomposition for virtual staging from a single panoramaACM Transactions on Graphics
2022 We describe a novel approach to decompose a single panorama of an empty indoor environment into four appearance components: specular, direct sunlight, diffuse and diffuse ambient without direct sunlight. Our system is weakly supervised by automatically generated semantic maps (with floor, wall, ceiling, lamp, window and door labels) that have shown success on perspective views and are trained for panoramas using transfer learning without any further annotations.
Generative Modeling for Multi-task Visual LearningProceedings of the 39th International Conference on Machine Learning
2022 Generative modeling has recently shown great promise in computer vision, but it has mostly focused on synthesizing visually realistic images. In this paper, motivated by multi-task learning of shareable feature representations, we consider a novel problem of learning a shared generative model that is useful across various visual perception tasks.