# Estimating 6D Pose From Localizing Designated Surface Keypoints

arXiv: https://arxiv.org/abs/1812.01387 · HTML: https://mlsanity.com/paper/1812.01387/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Dec 2018.

## Built on by (most cited first, 9 of 9)

- [RGB Matters: Learning 7-DoF Grasp Poses on Monocular RGBD Images](https://mlsanity.com/paper/2103.02184/) (2021)
- [SE(3) Diffusion Model-based Point Cloud Registration for Robust 6D Object Pose Estimation](https://mlsanity.com/paper/2310.17359/) (2023)
- [SuctionNet-1Billion: A Large-Scale Benchmark for Suction Grasping](https://mlsanity.com/paper/2103.12311/) (2021)
- [Deep Learning on Monocular Object Pose Detection and Tracking: A Comprehensive Overview](https://mlsanity.com/paper/2105.14291/) (2021)
- [ProTo: Program-Guided Transformer for Program-Guided Tasks](https://mlsanity.com/paper/2110.00804/) (2021)
- [Unseen Object 6D Pose Estimation: A Benchmark and Baselines](https://mlsanity.com/paper/2206.11808/) (2022)
- [End-to-end View Synthesis via NeRF Attention](https://mlsanity.com/paper/2207.14741/) (2022)
- [HccePose(BF): Predicting Front & Back Surfaces to Construct Ultra-Dense 2D-3D Correspondences for Pose Estimation](https://mlsanity.com/paper/2510.10177/) (2025)
- [6D Pose Estimation via Keypoint Heatmap Regression with RGB-D Residual Neural Networks](https://mlsanity.com/paper/2605.08059/) (2026)

## Abstract (arXiv)

In this paper, we present an accurate yet effective solution for 6D pose estimation from an RGB image. The core of our approach is that we first designate a set of surface points on target object model as keypoints and then train a keypoint detector (KPD) to localize them. Finally a PnP algorithm can recover the 6D pose according to the 2D-3D relationship of keypoints. Different from recent state-of-the-art CNN-based approaches that rely on a time-consuming post-processing procedure, our method can achieve competitive accuracy without any refinement after pose prediction. Meanwhile, we obtain a 30% relative improvement in terms of ADD accuracy among methods without using refinement. Moreover, we succeed in handling heavy occlusion by selecting the most confident keypoints to recover the 6D pose. For the sake of reproducibility, we will make our code and models publicly available soon.