{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/g2d-from-gta-to-data","title":"G2D: from GTA to Data","arxiv_id":"1806.07381","date":"2018-06-16","proceeding":null,"authors":["Anh-Dzung Doan","Abdul Mohsi Jawaid","Thanh-Toan Do","Tat-Jun Chin"],"abstract":"This document describes G2D, a software that enables capturing videos from\nGrand Theft Auto V (GTA V), a popular role playing game set in an expansive\nvirtual city. The target users of our software are computer vision researchers\nwho wish to collect hyper-realistic computer-generated imagery of a city from\nthe street level, under controlled 6DOF camera poses and varying environmental\nconditions (weather, season, time of day, traffic density, etc.).\n  G2D accesses/calls the native functions of the game; hence users can directly\ninteract with G2D while playing the game. Specifically, G2D enables users to\nmanipulate conditions of the virtual environment on the fly, while the gameplay\ncamera is set to automatically retrace a predetermined 6DOF camera pose\ntrajectory within the game coordinate system. Concurrently, automatic screen\ncapture is executed while the virtual environment is being explored. G2D and\nits source code are publicly available at https://goo.gl/SS7fS6\n  In addition, we demonstrate an application of G2D to generate a large-scale\ndataset with groundtruth camera poses for testing structure-from-motion (SfM)\nalgorithms. The dataset and generated 3D point clouds are also made available\nat https://goo.gl/DNzxHx","url_abs":"http://arxiv.org/abs/1806.07381v1","url_pdf":"http://arxiv.org/pdf/1806.07381v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"g2d-from-gta-to-data","repo_url":"https://github.com/Adelaide-AI-Group/G2D","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"g2d-from-gta-to-data","repo_url":"https://github.com/dadung/G2D","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"3d-reconstruction","task_name":"3D Reconstruction"},{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"visual-localization","task_name":"Visual Localization"},{"task_slug":"visual-place-recognition","task_name":"Visual Place Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1806.07381","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}