# Real-Time 6D Object Pose Estimation on CPU

arXiv: https://arxiv.org/abs/1811.08588 · HTML: https://mlsanity.com/paper/1811.08588/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Nov 2018.

## Built on by (most cited first, 7 of 7)

- [OV9D: Open-Vocabulary Category-Level 9D Object Pose and Size Estimation](https://mlsanity.com/paper/2403.12396/) (2024)
- [Transferring Experience from Simulation to the Real World for Precise Pick-And-Place Tasks in Highly Cluttered Scenes](https://mlsanity.com/paper/2101.04781/) (2021)
- [Video based Object 6D Pose Estimation using Transformers](https://mlsanity.com/paper/2210.13540/) (2022)
- [A Low-Cost, High-Speed, and Robust Bin Picking System for Factory Automation Enabled by a Non-Stop, Multi-View, and Active Vision Scheme](https://mlsanity.com/paper/2410.00706/) (2024)
- [A Collision-Aware Cable Grasping Method in Cluttered Environment](https://mlsanity.com/paper/2402.14498/) (2024)
- [VideoPose: Estimating 6D object pose from videos](https://mlsanity.com/paper/2111.10677/) (2021)
- [Precise Object Placement with Pose Distance Estimations for Different Objects and Grippers](https://mlsanity.com/paper/2110.00992/) (2021)

## Abstract (arXiv)

We propose a fast and accurate 6D object pose estimation from a RGB-D image. Our proposed method is template matching based and consists of three main technical components, PCOF-MOD (multimodal PCOF), balanced pose tree (BPT) and optimum memory rearrangement for a coarse-to-fine search. Our model templates on densely sampled viewpoints and PCOF-MOD which explicitly handles a certain range of 3D object pose improve the robustness against background clutters. BPT which is an efficient tree-based data structures for a large number of templates and template matching on rearranged feature maps where nearby features are linearly aligned accelerate the pose estimation. The experimental evaluation on tabletop and bin-picking dataset showed that our method achieved higher accuracy and faster speed in comparison with state-of-the-art techniques including recent CNN based approaches. Moreover, our model templates can be trained only from 3D CAD in a few minutes and the pose estimation run in near real-time (23 fps) on CPU. These features are suitable for any real applications.