computer-vision
computer-vision

computer-vision

Abdul Latif Jameel Water and Food Systems Lab (J-WAFS) Algorithms Animals Artificial Intelligence computer-vision Data Ecology Electrical engineering and computer science (EECS) Environment Faculty Food machine learning Research School of Engineering Sustainability

Streamlining data collection for improved salmon population management

Assistant Professor Sara Beery is using automation to improve monitoring of migrating salmon in the Pacific Northwest.

Aeronautical and astronautical engineering Algorithms Artificial Intelligence Automation Autonomous vehicles computer-vision Drones Faculty Laboratory for Information and Decision Systems (LIDS) MIT Schwarzman College of Computing Profile Robotics School of Engineering Software

Expanding robot perception

Associate Professor Luca Carlone is working to give robots a more human-like awareness of their environment.

Algorithms Animals Artificial Intelligence Computer Science and Artificial Intelligence Laboratory (CSAIL) Computer science and technology computer-vision Data Ecology Electrical engineering and computer science (EECS) machine learning MIT Schwarzman College of Computing Research School of Engineering

Ecologists find computer vision models’ blind spots in retrieving wildlife images

Biodiversity researchers tested vision systems on how well they could retrieve relevant nature images. More advanced models performed well on simple queries but struggled with more research-specific prompts.

Algorithms Artificial Intelligence Computer Science and Artificial Intelligence Laboratory (CSAIL) Computer science and technology computer-vision Electrical engineering and computer science (EECS) machine learning MIT Schwarzman College of Computing Natural language processing Quest for Intelligence Research Robotics School of Engineering

Teaching a robot its limits, to complete open-ended tasks safely

The “PRoC3S” method helps an LLM create a viable action plan by testing each step in a simulation. This strategy could eventually aid in-home robots to complete more ambiguous chore requests.

Algorithms Artificial Intelligence Arts Augmented and virtual reality Computer Science and Artificial Intelligence Laboratory (CSAIL) Computer science and technology computer-vision Electrical engineering and computer science (EECS) machine learning MIT Schwarzman College of Computing MIT-IBM Watson AI Lab National Science Foundation (NSF) Research School of Engineering

A new way to create realistic 3D shapes using generative AI

Researchers propose a simple fix to an existing technique that could help artists, designers, and engineers create better 3D models.

Aeronautical and astronautical engineering Artificial Intelligence Climate change computer-vision Disaster response EAPS Earth and atmospheric sciences Environment Hurricanes Imaging machine learning Media Lab NASA Research Satellites School of Engineering School of Science Science communications Weather

New AI tool generates realistic satellite images of future flooding

The method could help communities visualize and prepare for approaching storms.

Artificial Intelligence Computer Science and Artificial Intelligence Laboratory (CSAIL) Computer science and technology computer-vision Data Electrical engineering and computer science (EECS) Human-computer interaction machine learning MIT Schwarzman College of Computing Research Robotics School of Engineering

Can robots learn from machine dreams?

MIT CSAIL researchers used AI-generated images to train a robot dog in parkour, without real-world data. Their LucidSim system demonstrates generative AI’s potential for creating robotics training data.

Artificial Intelligence Computer Science and Artificial Intelligence Laboratory (CSAIL) Computer science and technology computer-vision Electrical engineering and computer science (EECS) machine learning MIT Schwarzman College of Computing Research Robotics School of Engineering Video

Combining next-token prediction and video diffusion in computer vision and robotics

A new method can train a neural network to sort corrupted data while anticipating next steps. It can make flexible plans for robots, generate high-quality video, and help AI agents navigate digital environments.

Algorithms Artificial Intelligence Brain and cognitive sciences Computer Science and Artificial Intelligence Laboratory (CSAIL) Computer science and technology computer-vision Electrical engineering and computer science (EECS) Evolution Imaging Lincoln Laboratory machine learning MIT Schwarzman College of Computing Psychology Research School of Engineering School of Science

AI pareidolia: Can machines spot faces in inanimate objects?

New dataset of “illusory” faces reveals differences between human and algorithmic face detection, links to animal face recognition, and a formula predicting where people most often perceive faces.

Aeronautical and astronautical engineering Algorithms Artificial Intelligence Autonomous vehicles computer-vision Disaster response Laboratory for Information and Decision Systems (LIDS) Lincoln Laboratory machine learning MIT Schwarzman College of Computing Natural disasters Research Robotics School of Engineering

Helping robots zero in on the objects that matter

A new method called Clio enables robots to quickly map a scene and identify the items they need to complete a given set of tasks.