{"id":13444369,"url":"https://github.com/YoungXIAO13/ObjectPoseEstimationSummary","last_synced_at":"2025-03-20T18:32:28.593Z","repository":{"id":35347325,"uuid":"197577488","full_name":"YoungXIAO13/ObjectPoseEstimationSummary","owner":"YoungXIAO13","description":"Resources (papers, datasets, rendering methods) in the domain of object pose estimation.","archived":false,"fork":false,"pushed_at":"2023-07-09T09:55:31.000Z","size":16742,"stargazers_count":701,"open_issues_count":1,"forks_count":87,"subscribers_count":28,"default_branch":"master","last_synced_at":"2024-08-01T04:02:07.690Z","etag":null,"topics":[],"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/YoungXIAO13.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":"2019-07-18T11:52:58.000Z","updated_at":"2024-07-26T09:02:21.000Z","dependencies_parsed_at":"2023-01-15T19:00:21.468Z","dependency_job_id":"6d8452f8-a3ee-4899-81b6-a6a4a2a6913b","html_url":"https://github.com/YoungXIAO13/ObjectPoseEstimationSummary","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/YoungXIAO13%2FObjectPoseEstimationSummary","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YoungXIAO13%2FObjectPoseEstimationSummary/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YoungXIAO13%2FObjectPoseEstimationSummary/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YoungXIAO13%2FObjectPoseEstimationSummary/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/YoungXIAO13","download_url":"https://codeload.github.com/YoungXIAO13/ObjectPoseEstimationSummary/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":221792892,"owners_count":16881289,"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":[],"created_at":"2024-07-31T04:00:21.041Z","updated_at":"2024-10-28T06:30:45.152Z","avatar_url":"https://github.com/YoungXIAO13.png","language":"Python","funding_links":[],"categories":["Uncategorized","Datasets"],"sub_categories":["Uncategorized","Benchmark-6D-Object-Pose-Estimation"],"readme":"# Awesome Object Pose Estimation [\\[Paper List\\]](https://github.com/YoungXIAO13/ObjectPoseEstimationSummary/blob/master/paper.md)\nA repo to summarize resources used in object pose estimation as well as viewpoint estimation.\n\nIn the following tables, 3D CAD model is noted as **model** and 2D pictured object is noted as **object**.\n\n## Contributing\nContributions are welcome.\nPlease see the **Table of Content** which lists the things included in this repo.\nIf you wish to contribute within these boundaries, feel free to send a PR.\nIf you have suggestions for new sections to be included, please raise an issue and discuss before sending a PR.\n\n\n## Table of Content\n* [Resources :sunglasses:](https://github.com/YoungXIAO13/ObjectPoseEstimationSummary/blob/master/paper.md)\n* [Objects in the wild :camera:](#objects-in-the-wild-camera)\n* [Objects in the controlled environments :movie_camera:](#objects-in-the-controlled-environments-movie_camera)\n* [3D model datasets :bike:](#3d-model-datasets-bike)\n* [Rendering methods :bicyclist:](#rendering-methods-mountain_bicyclist)\n\n\n## Objects in the wild :camera:\nIn this table, **Pix3D** provides accurate 2D-3D alignment\nwhile others provide a coarse alignment.\n\n**PASCAL3D+** is the de facto benchmark used for viewpoint estimation.\n\n| Dataset | Sample image | Annotation | Statistics | Reference |\n| :-----: | :-----: | :-----: | :-----: | :-----: |\n| [Objectron](https://github.com/google-research-datasets/Objectron/) | ![](https://github.com/google-research-datasets/Objectron/blob/master/docs/images/objectron_samples.gif) | 3D Bounding Box | **15K** annotated videos and **4M** annotated images | [CVPR 2021](https://openaccess.thecvf.com/content/CVPR2021/html/Ahmadyan_Objectron_A_Large_Scale_Dataset_of_Object-Centric_Videos_in_the_CVPR_2021_paper.html) |\n| [ApolloCar3D](http://apolloscape.auto/car_instance.html) | ![](https://github.com/YoungXIAO13/6DPoseEstimationDatasets/blob/master/img/ApolloCar3D.png) | 6D Pose + Mask | **34** car models with **60K+** objects in **5,277** images | [CVPR 2019](https://arxiv.org/abs/1811.12222) |\n| [Pix3D](http://pix3d.csail.mit.edu/) | ![](https://github.com/YoungXIAO13/6DPoseEstimationDatasets/blob/master/img/Pix3D.png) | 6D Pose + Mask | **9** categories containing **395 models** in **10,069** images | [CVPR 2018](http://pix3d.csail.mit.edu/papers/pix3d_cvpr.pdf) |\n| [ObjectNet3D](http://cvgl.stanford.edu/projects/objectnet3d/) | ![](https://github.com/YoungXIAO13/6DPoseEstimationDatasets/blob/master/img/ObjectNet3D.png) | Euler Angles + BoundingBox | **100** categories with **201,888** objects in **90,127** images | [ECCV 2016](http://cvgl.stanford.edu/papers/xiang_eccv16.pdf) |\n| [PASCAL3D+](http://cvgl.stanford.edu/projects/pascal3d.html) | ![](https://github.com/YoungXIAO13/6DPoseEstimationDatasets/blob/master/img/Pascal3D.png) | Euler Angles + BoundingBox | **12** categories with **36,292** objects in **30,889** images | [WACV 2014](https://www-cs.stanford.edu/~roozbeh/papers/wacv14.pdf) |\n| [KITTI](http://www.cvlibs.net/datasets/kitti/eval_object.php) | ![](https://github.com/YoungXIAO13/6DPoseEstimationDatasets/blob/master/img/KITTI.png) | 3D BoundingBox | **80,256** objects in **14,999** images | [CVPR 2012](http://www.cvlibs.net/publications/Geiger2012CVPR.pdf) |\n\n\n\n## Objects in the controlled environments :movie_camera:\nThis table lists the datasets commonly known as **BOP: Benchmark 6D Object Pose Estimation**,\nwhich provide accurate 3D object models and accurate 2D-3D alignment.\n\nYou can download all the BOP datasets [**here**](https://bop.felk.cvut.cz/datasets/) and\nuse the [**toolkit**](https://github.com/thodan/bop_toolkit) provided by the organizers.\n\nAfter downloading the data,\nyou can use our code ```data/BOP/ply2obj.py``` to convert original **.ply** files to **.obj** files,\nand run ```data/BOP/create_annotation.py``` to create a single annotation file for all the scenes in a dataset.\n\nDatasets format can be found [here](https://github.com/thodan/bop_toolkit/blob/master/docs/bop_datasets_format.md),\nwe use **instance id** in our annotation to indicate different instances pictured in the same image.\n\n| Dataset | Sample image | Annotation | Statistics | Reference |\n| :-----: | :-----: | :-----: | :-----: | :-----: |\n| [GraspNet-1B](https://graspnet.net/index.html) | ![](https://graspnet.net/images/datakn.gif) | 6D pose + Depth + Mask| **88** models in **190** videos with **97,280** frames| [CVPR 2020](https://openaccess.thecvf.com/content_CVPR_2020/papers/Fang_GraspNet-1Billion_A_Large-Scale_Benchmark_for_General_Object_Grasping_CVPR_2020_paper.pdf)|\n| [NOCS](https://hughw19.github.io/NOCS_CVPR2019) | ![](https://github.com/YoungXIAO13/6DPoseEstimationDatasets/blob/master/img/nocs_real.jpg) | 6D pose + Depth + NOCS| **6** categories in **300K** composited images and **8K** real images| [CVPR 2019](https://arxiv.org/abs/1901.02970)|\n| [YCBInEOAT](https://github.com/wenbowen123/iros20-6d-pose-tracking) | ![](https://github.com/wenbowen123/BundleTrack/blob/master/media/vis_video_bleach0_method_ours_c.gif) | 6D pose + RGBD Video| **5** models in **9** videos with **7449** frames with **moving** objects| [IROS 2020](https://arxiv.org/pdf/2007.13866.pdf)|\n| [YCB-Video](https://rse-lab.cs.washington.edu/projects/posecnn/) | ![](https://github.com/YoungXIAO13/6DPoseEstimationDatasets/blob/master/img/YCB-Video.png) | 6D Pose + Depth + Mask | **21** models in **92** videos with **133,827** frames| [RSS 2018](https://arxiv.org/abs/1711.00199) |\n| [T-LESS](http://cmp.felk.cvut.cz/t-less/)| ![](https://github.com/YoungXIAO13/6DPoseEstimationDatasets/blob/master/img/T-LESS.png) | 6D Pose + Depth | **30** models in **20** videos with **~49K** frames | [WACV 2017](https://arxiv.org/abs/1701.05498)|\n| [Doumanoglou](http://rkouskou.gitlab.io/research/6D_NBV.html)| ![](https://bop.felk.cvut.cz/media/icbin_thumb_gt.jpg)| 6D Pose + Depth | **2** models in **3** videos with **183** frames| [CVPR 2016](https://arxiv.org/abs/1512.07506)|\n| [Tejani](http://rkouskou.gitlab.io/research/LCHF.html) | ![](https://bop.felk.cvut.cz/media/icmi_thumb_gt.jpg) | 6D Pose + Depth | **6** models in **6** videos with **2,067** frames | [ECCV 2014](http://rkouskou.gitlab.io/publications/docs/ECCV_2014.pdf)|\n| [Occluded-LINEMOD](https://bop.felk.cvut.cz/datasets/) | ![](https://github.com/YoungXIAO13/6DPoseEstimationDatasets/blob/master/img/LINEMOD-O.jpg) | 6D Pose + Depth | **8** models in **1,214** frames with **8,992** objects | [ECCV 2014](http://wwwpub.zih.tu-dresden.de/~cvweb/publications/papers/2014/PoseEstimationECCV2014.pdf) |\n| [LINEMOD](https://bop.felk.cvut.cz/datasets/) | ![](https://github.com/YoungXIAO13/6DPoseEstimationDatasets/blob/master/img/LINEMOD.jpg) | 6D pose + Depth for one object | **15** models in **15** videos with **18,273** frames | [ACCV 2012](http://www.stefan-hinterstoisser.com/papers/hinterstoisser2012accv.pdf) |\n\n\n## 3D model datasets :bike:\nIn order to testify the network **generalization** ability\n(tested on images containing **unseen** 3D models from the training set),\nthe following dataset could be used to generate synthetic training data.\n\nNotice that **ABC** contains generic and arbitrary industrial CAD models\nwhile **ShapeNetCore** and **ModelNet** contain common category objects such as cars and chairs.\n\n| Dataset | Categories | Models in total | Reference |\n| :-----: | :-----: | :-----: | :-----: |\n| [ABC](https://deep-geometry.github.io/abc-dataset/) | - | 1 million | [CVPR 2019](https://arxiv.org/pdf/1812.06216.pdf) |\n| [ShapeNetCore](https://www.shapenet.org/download/shapenetcore) | 55 | ~51,300 | [ArXiv 2015](https://arxiv.org/abs/1512.03012) |\n| [ModelNet-40](http://modelnet.cs.princeton.edu/) | 40 | 12,311 | [CVPR 2015](https://3dshapenets.cs.princeton.edu/paper.pdf) |\n\n\n## Rendering methods :mountain_bicyclist:\n\n### Differentiable Renderer\n* [Neural 3D Mesh Renderer](http://hiroharu-kato.com/projects_en/neural_renderer.html): Kato el al. CVPR 2018\n\n* [RenderNet](https://github.com/thunguyenphuoc/RenderNet): Thu et al. NIPS 2018\n\n### Blender Render :\n\n* [BlenderProc](https://github.com/DLR-RM/BlenderProc)\n\n* [blender-cli-rendering](https://github.com/yuki-koyama/blender-cli-rendering)\n\n* [pvnet-rendering](https://github.com/zju3dv/pvnet-rendering)\n\n* [bpycv](https://github.com/DIYer22/bpycv)\n\n### Physical Simulator\n\n[PyBullet](https://github.com/bulletphysics/bullet3/tree/master/examples/pybullet):\na very popular one in the Robotics community.\n\n\n### Others\n* [Glumpy](https://github.com/glumpy/glumpy): does not support headless rendering (failed on ssh mode)\n\n* [UnrealCV](https://github.com/unrealcv/unrealcv): extension of Unreal Engine 4,\nhelps interact with virtual world and communicate with external program.\n\n* [SyntheticComputerVision](https://github.com/unrealcv/synthetic-computer-vision):\nresuming a lot of techniques used to generate synthetic image\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FYoungXIAO13%2FObjectPoseEstimationSummary","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FYoungXIAO13%2FObjectPoseEstimationSummary","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FYoungXIAO13%2FObjectPoseEstimationSummary/lists"}