{ "@context": "http://schema.org", "@type": "Event", "name": "Synthetic Data Generation for 3D Mesh Prediction and Spatial Reasoning During Multi-Agent Robotic Missions", "startDate": "2021-01", "location": { "@type": "Place", "name": "AIAA SciTech Forum", "address": { "@type": "PostalAddress", "addressLocality": "Location of conference (if known)", "addressRegion": "Region of conference (if known)", "addressCountry": "Country of conference (if known)" } }, "sponsor": { "@type": "Organization", "name": "American Institute of Aeronautics and Astronautics (AIAA)" }, "performer": [ { "@type": "Person", "name": "James Ecker" }, { "@type": "Person", "name": "Benjamin Kelley" }, { "@type": "Person", "name": "Danette Allen" } ], "workFeatured": [ { "@type": "CreativeWork", "name": "Computer Vision During In-Space Assembly", "about": "Difficulties in space operations such as illumination, angle, orientation, movement, energy, and mass constraints." }, { "@type": "CreativeWork", "name": "Mask R-CNN and Mesh R-CNN in Space Technology", "about": "Techniques for instance segmentation and 3D mesh prediction in space robotics." }, { "@type": "CreativeWork", "name": "Synthesizing Data for Space Robotics", "about": "Using tools like Blender, ROS, Gazebo, and Mujoco for creating synthetic datasets for computer vision systems." } ], "about": { "@type": "Thing", "name": "Computer Vision and Robotics in Space", "description": "The presentation covers topics such as synthetic data generation, computer vision challenges in space, mitigation of resource constraints, and advancements in 3D mesh prediction models." }, "keywords": [ "Synthetic Data", "3D Mesh Prediction", "Spatial Reasoning", "Robotics", "Computer Vision", "In-Space Assembly", "AI", "Machine Learning", "Deep Learning", "GANs", "PointCloud Generation" ], "citation": [ { "@type": "CreativeWork", "name": "Mask R-CNN", "author": [ { "@type": "Person", "name": "Kaiming He" }, { "@type": "Person", "name": "Georgia Gkioxari" }, { "@type": "Person", "name": "Piotr Dollár" }, { "@type": "Person", "name": "Ross Girshick" } ], "datePublished": "2017", "url": "https://doi.org/10.1109/ICCV.2017.322" }, { "@type": "CreativeWork", "name": "Mesh R-CNN", "author": [ { "@type": "Person", "name": "Georgia Gkioxari" }, { "@type": "Person", "name": "Jitendra Malik" } ], "datePublished": "2019", "url": "https://doi.org/10.1109/ICCV.2019.00988" }, { "@type": "CreativeWork", "name": "Assistive Relative Pose Estimation for On-orbit Assembly using Convolutional Neural Networks", "author": { "@type": "Person", "name": "S. D. Sonawani et al." }, "datePublished": "2020", "url": "http://arxiv.org/abs/2001.10673" }, { "@type": "CreativeWork", "name": "3D Point Cloud Generation from 2D Depth Camera Images using Successive Triangulation", "author": { "@type": "Person", "name": "B. Pal et al." }, "datePublished": "2017", "url": "https://doi.org/10.1109/ICIMIA.2017.7975586" }, { "@type": "CreativeWork", "name": "Learning Localized Representations of Point Clouds with Graph-Convolutional Generative Adversarial Networks", "author": { "@type": "Person", "name": "D. Valsesia et al." }, "datePublished": "2019", "url": "https://ieeexplore.ieee.org/document/8642330" }, { "@type": "CreativeWork", "name": "Spectral-GANs for High Resolution 3D Point Cloud Generation", "author": { "@type": "Person", "name": "S. Ramasinghe et al." }, "datePublished": "2019", "url": "http://arxiv.org/abs/1912.01800" } ] }