The shared mission of Visual Computing is to connect images and computation, spanning topics such as image and video generation and analysis, photography, human perception, touch, applied geometry, and more.
We study the problem of 3D object generation. We propose a novel framework, 3D Generative Adversarial Network (3D-GAN), leveraging recent advances in volumetric convolutional networks and generative adversarial nets.
Automatic speech recognition (ASR) has been a grand challenge machine learning problem for decades. Our ongoing research in this area examines the use of deep learning models for distant and noisy recording conditions, multilingual, and low-resource scenarios.
Our goal is to develop collaborative agents (software or robots) that can efficiently communicate with their human teammates. Key threads involve designing algorithms for inferring human behavior and for decision-making under uncertainty.
We aim to understand 3D object structure from a single image. We propose an end-to-end framework which sequentially estimates 2D keypoint heatmaps and 3D object structure, by training it on both real 2D-annotated images and synthetic 3D data and by integrating a 3D-to-2D projection layer.
Developed at MIT’s Computer Science and Artificial Intelligence Laboratory, a team of robots can self-assemble to form different structures with applications in inspection, disaster response, and manufacturing
Google AI’s Jeff Dean has a seemingly straightforward objective: he wants to use a collection of trainable mathematical units organized in layers to solve complicated tasks that will ultimately benefit many parts of society.