{"id":13613163,"url":"https://github.com/angeladai/3DMV","last_synced_at":"2025-04-13T15:32:42.431Z","repository":{"id":84144546,"uuid":"141841852","full_name":"angeladai/3DMV","owner":"angeladai","description":"[ECCV'18] 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation","archived":false,"fork":false,"pushed_at":"2022-02-22T14:59:16.000Z","size":790,"stargazers_count":208,"open_issues_count":5,"forks_count":40,"subscribers_count":13,"default_branch":"master","last_synced_at":"2024-08-02T20:45:12.339Z","etag":null,"topics":["computer-graphics","computer-vision","deep-learning","scene-understanding"],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/angeladai.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":"2018-07-21T19:51:40.000Z","updated_at":"2024-07-08T05:07:01.000Z","dependencies_parsed_at":null,"dependency_job_id":"56019b53-5ee5-45d5-a105-a3e4ddc26db6","html_url":"https://github.com/angeladai/3DMV","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/angeladai%2F3DMV","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/angeladai%2F3DMV/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/angeladai%2F3DMV/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/angeladai%2F3DMV/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/angeladai","download_url":"https://codeload.github.com/angeladai/3DMV/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":223592503,"owners_count":17170500,"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":["computer-graphics","computer-vision","deep-learning","scene-understanding"],"created_at":"2024-08-01T20:00:40.907Z","updated_at":"2024-11-07T21:30:47.859Z","avatar_url":"https://github.com/angeladai.png","language":"Python","funding_links":[],"categories":["Deep Learning"],"sub_categories":[],"readme":"# 3DMV\n\n3DMV jointly combines RGB color and geometric information to perform 3D semantic segmentation of RGB-D scans. This work is based on our ECCV'18 paper, [\n3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation](https://arxiv.org/pdf/1803.10409.pdf).\n\n[\u003cimg src=\"images/teaser.jpg\"\u003e](https://arxiv.org/abs/1803.10409)\n\n\n## Code\n### Installation:  \nTraining is implemented with [PyTorch](https://pytorch.org/). This code was developed under PyTorch 0.2 and recently upgraded to PyTorch 0.4.\n\n### Training:  \n* See `python train.py --help` for all train options. \nExample train call:\n```\npython train.py --gpu 0 --train_data_list [path to list of train files] --data_path_2d [path to 2d image data] --class_weight_file [path to txt file of train histogram] --num_nearest_images 5 --model2d_path [path to pretrained 2d model]\n```\n* Trained models: [models.zip](http://kaldir.vc.in.tum.de/adai/3DMV/models.zip)\n\n### Testing\n* See `python test.py --help` for all test options. \nExample test call:\n```\npython test.py --gpu 0 --scene_list test_scenes.txt --model_path models/scannetv2/scannet5_model.pth --data_path_2d [path to 2d image data] --data_path_3d [path to test scene data] --num_nearest_images 5 --model2d_orig_path models/scannetv2/scannet5_model2d.pth\n```\n\n### Data:\nThis data has been precomputed from the [ScanNet](http://www.scan-net.org/) (v2) dataset.\n* Train data for ScanNet v2: [3dmv_scannet_v2_train.zip](http://kaldir.vc.in.tum.de/adai/3DMV/data/3dmv_scannet_v2_train.zip) (6.2G)\n    * 2D train images can be processed from the ScanNet dataset using the 2d data preparation script in [prepare_data](prepare_data)\n    * Expected file structure for 2D data:\n    ```\n    scene0000_00/\n    |--color/\n       |--[framenum].jpg\n           ⋮\n    |--depth/\n       |--[framenum].png   (16-bit pngs)\n           ⋮\n    |--pose/\n       |--[framenum].txt   (4x4 rigid transform as txt file)\n           ⋮\n    |--label/    (if applicable)\n       |--[framenum].png   (8-bit pngs)\n           ⋮\n    scene0000_01/\n    ⋮\n    ```\n* Test scenes for ScanNet v2: [3dmv_scannet_v2_test_scenes.zip](http://kaldir.vc.in.tum.de/adai/3DMV/data/3dmv_scannet_v2_test_scenes.zip) (110M)\n\n\n## Citation:  \nIf you find our work useful in your research, please consider citing:\n```\n@inproceedings{dai20183dmv,\n author = {Dai, Angela and Nie{\\ss}ner, Matthias},\n booktitle = {Proceedings of the European Conference on Computer Vision ({ECCV})},\n title = {3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation},\n year = {2018}\n}\n```\n\n## Contact:\nIf you have any questions, please email Angela Dai at adai@cs.stanford.edu.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fangeladai%2F3DMV","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fangeladai%2F3DMV","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fangeladai%2F3DMV/lists"}