Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
[IJCV 2026] Project Page for "Deep Learning-Based Object Pose Estimation: A Comprehensive Survey".
| Date | Stars |
|---|---|
| 2026-07-31 | 442 |
| 2026-08-02 | 443 |
| 2026-08-06 | 445 |
Today
+2 stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="center"> # [IJCV'26] Deep Learning-Based Object Pose Estimation: A Comprehensive Survey [Jian Liu](https://cnjliu.github.io/), [Wei Sun](http://robotics.hnu.edu.cn/info/1071/1265.htm), [Hui Yang](https://scholar.google.com/citations?user=rhQSwuoAAAAJ&hl=zh-CN), [Zhiwen Zeng](https://github.com/CNJianLiu/Awesome-Object-Pose-Estimation/), [Chongpei Liu](https://github.com/CNJianLiu/Awesome-Object-Pose-Estimation/), [Jin Zheng](https://github.com/CNJianLiu/Awesome-Object-Pose-Estimation/), [Xingyu Liu](https://lliu-xingyu.github.io/), [Hossein Rahmani](https://sites.google.com/view/rahmaniatlu), [Nicu Sebe](https://scholar.google.com.hk/citations?user=stFCYOAAAAAJ&hl=zh-CN&oi=ao), [Ajmal Mian](https://ajmalsaeed.net/) ### [1. Introduction](#1-introduction) | [2. Datasets](#2-datasets) ### [3. Instance-Level](#3-instance-level) | [4. Category-Level](#4-category-level) | [5. Unseen](#5-unseen) | [6. Applications](#6-applications) </div> Note: For any missing or recently published papers, feel free to pull a request, we will add them asap :) ## 1. Introduction This is the official repository of paper [''Deep Learning-Based Object Pose Estimation: A Comprehensive Survey''](https://link.springer.com/article/10.1007/s11263-025-02646-6) published in <b>*IJCV*</b>. Specifically, we first introduce the [datasets](#2-datasets) used for object pose estimation. Then, we review the [instance-level](#3-instance-level), [category-level](#4-category-level), and [unseen](#5-unseen) methods, respectively. Finally, we summarize the common [applications](#6-applications) of this task. The taxonomy of this survey is shown as follows <p align="center"> <img src="./resources/taxonomy.png" width="100%"> </p> A comparison of instance-level, category-level, and unseen methods is shown as follows. Instance-level methods can only estimate the pose of specific object instances on which they are trained. Category-level methods can infer intra-class unseen instances rather than being limited to specific instances in the training data. In contrast, unseen object pose estimation methods have stronger generalization ability and can handle object categories not encountered during training. <p align="center"> <img src="./resources/Fig0.jpg" width="100%"> </p> ## 2. Datasets Chronological overview of the datasets for object pose estimation evaluation. Notably, the pink arrows represent the BOP Challenge datasets, which can be used to evaluate both instance-level and unseen object methods. The red references represent the datasets of articulated objects. <p align="center"> <img src="./resources/datasets.png" width="100%"> </p> ### 2.1 Datasets for Instance-Level Methods <details> <summary>All Datasets</summary> - BOP Challenge Datasets [[Paper]](https://arxiv.org/abs/2403.09799) [[Data]](https://bop.felk.cvut.cz/challenges/bop-challenge-2023/) - YCBInEOAT Dataset [[Paper]](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9341314) [[Data]](https://github.com/wenbowen123/iros20-6d-pose-tracking) - ClearPose Dataset [[Paper]](https://link.springer.com/chapter/10.1007/978-3-031-20074-8_22) [[Data]](https://github.com/opipari/ClearPose) - MP6D Dataset [[Paper]](https://ieeexplore.ieee.org/abstract/document/9722997) [[Data]](https://github.com/yhan9848/MP6D) </details> ### 2.2 Datasets for Category-Level Methods <details> <summary>2.2.1 Rigid Objects Datasets</summary> - CAMERA25 Dataset [[Paper]](https://openaccess.thecvf.com/content_CVPR_2019/papers/Wang_Normalized_Object_Coordinate_Space_for_Category-Level_6D_Object_Pose_and_CVPR_2019_paper.pdf) [[Data]](https://github.com/hughw19/NOCS_CVPR2019) - REAL275 Dataset [[Paper]](https://openaccess.thecvf.com/content_CVPR_2019/papers/Wang_Normalized_Object_Coordinate_Space_for_Category-Level_6D_Object_Pose_and_CVPR_2019_paper.pdf) [[Data]](https://github.com/hughw19/NOCS_CVPR2019) - kPAM Dataset [[Paper]](https://link.springer.com/chapter/10.1007/978-3-030-95459-8_9) [[Data]](https://site
Excerpt of 69,192 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:39cae44a2a047003, topic:pose-estimation, name:pose estimation, desc:pose estimation
matched fp:39cae44a2a047003, topic:awesome, topic:awesome-list