{"id":15654228,"url":"https://github.com/yyong119/im2cad","last_synced_at":"2025-10-17T10:02:06.422Z","repository":{"id":72373141,"uuid":"119008423","full_name":"yyong119/IM2CAD","owner":"yyong119","description":"Unofficial code for IM2CAD","archived":false,"fork":false,"pushed_at":"2018-03-01T04:51:00.000Z","size":16,"stargazers_count":24,"open_issues_count":2,"forks_count":7,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-02-25T12:04:52.914Z","etag":null,"topics":["deep-learning","im2cad","lsun","tensorflow"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/yyong119.png","metadata":{"files":{"readme":"readme.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2018-01-26T05:12:35.000Z","updated_at":"2024-10-01T15:00:03.000Z","dependencies_parsed_at":"2023-04-10T15:33:49.551Z","dependency_job_id":null,"html_url":"https://github.com/yyong119/IM2CAD","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yyong119%2FIM2CAD","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yyong119%2FIM2CAD/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yyong119%2FIM2CAD/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yyong119%2FIM2CAD/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/yyong119","download_url":"https://codeload.github.com/yyong119/IM2CAD/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":242718448,"owners_count":20174339,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["deep-learning","im2cad","lsun","tensorflow"],"created_at":"2024-10-03T12:50:01.977Z","updated_at":"2025-10-17T10:02:06.284Z","avatar_url":"https://github.com/yyong119.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# IM2CAD\n\nIt's a repository trying to achieve the idea in paper \u003ca href = \"https://homes.cs.washington.edu/~izadinia/im2cad.html\"\u003eIM2CAD\u003c/a\u003e. The main goal of this paper is to reconstruct a scene that is similar to the given photo of a room.\n\n## Datasets used in the paper\n\n- \u003ca href = \"http://tigress-web.princeton.edu/~fy/lsun/public/release/\"\u003eLSUN\u003c/a\u003e is needed in pixel-level labeling task to estimate the room geometry.\n\n- \u003ca href = \"http://www.image-net.org/challenges/LSVRC/2012/nonpub-downloads\"\u003eimagenet2012\u003c/a\u003e dataset is used to detect the objects in the room(pre-trained model was used in the paper).\n\n- \u003ca href = \"https://www.shapenet.org/\"\u003eShapeNet\u003c/a\u003e 3D models are the objects will appear in the reconstructed scene. (an account may needed to download data)\n\n## Main Process to achieve the result\n\n#### Room geometry estimation\n\nThe lsun indoor dataset can be downloaded from the above link, or you can fork the official GitHub repository \u003ca href = \"https://github.com/fyu/lsun\"\u003elsun\u003c/a\u003e and follow the instructions there.\n\nThe FCN is modified from the repo \u003ca href = \"https://github.com/shekkizh/FCN.tensorflow\"\u003eFCN.tensorflow\u003c/a\u003e. Note: The format of lsun indoor dataset is different a bit from the ADEChallengeData2016 dataset which is used in the origin repository.\n\nTo train the network, just running the following command:\n\n```shell\npython FCN.py --mode=train\n```\n\nIt can also visualize the part of results by replacing the \"train\" with \"visualize\".\n\n#### Object detection\n\nAccording to the paper, the Faster-RCNN is used to detect the objects occured in the indoor scene.","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyyong119%2Fim2cad","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fyyong119%2Fim2cad","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyyong119%2Fim2cad/lists"}