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.
To achieve high-quality photo lighting in challenging environments, our prototype camera dynamically reconstructs a 3D scene model and directs a motor-controlled flash head at nearby walls and ceilings for soft indirect illumination.
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.
Our goal is to build a system that predicts where people are looking in images. Given an image and the location of a head, our approach follows the gaze of the person and identifies the object being looked at.
In recent years, a host of Hollywood blockbusters — including “The Fast and the Furious 7,” “Jurassic World,” and “The Wolf of Wall Street” — have included aerial tracking shots provided by drone helicopters outfitted with cameras. Those shots required separate operators for the drones and the cameras, and careful planning to avoid collisions. But a team of researchers from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) and ETH Zurich hope to make drone cinematography more accessible, simple, and reliable.