# Robust 6D Object Pose Estimation by Learning RGB-D Features

arXiv: https://arxiv.org/abs/2003.00188 · HTML: https://mlsanity.com/paper/2003.00188/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Feb 2020.

## Built on by (most cited first, 25 of 25)

- [ClearPose: Large-scale Transparent Object Dataset and Benchmark](https://mlsanity.com/paper/2203.03890/) (2022)
- [StereOBJ-1M: Large-scale Stereo Image Dataset for 6D Object Pose Estimation](https://mlsanity.com/paper/2109.10115/) (2021)
- [Deep Learning-Based Object Pose Estimation: A Comprehensive Survey](https://mlsanity.com/paper/2405.07801/) (2024)
- [3DP3: 3D Scene Perception via Probabilistic Programming](https://mlsanity.com/paper/2111.00312/) (2021)
- [Sim-to-Real 6D Object Pose Estimation via Iterative Self-training for Robotic Bin Picking](https://mlsanity.com/paper/2204.07049/) (2022)
- [Play to the Score: Stage-Guided Dynamic Multi-Sensory Fusion for Robotic Manipulation](https://mlsanity.com/paper/2408.01366/) (2024)
- [Orienting Novel 3D Objects Using Self-Supervised Learning of Rotation Transforms](https://mlsanity.com/paper/2105.14246/) (2021)
- [Multi-person Implicit Reconstruction from a Single Image](https://mlsanity.com/paper/2104.09283/) (2021)
- [TransNet: Category-Level Transparent Object Pose Estimation](https://mlsanity.com/paper/2208.10002/) (2022)
- [Robust Partial-to-Partial Point Cloud Registration in a Full Range](https://mlsanity.com/paper/2111.15606/) (2021)
- [Keypoint Cascade Voting for Point Cloud Based 6DoF Pose Estimation](https://mlsanity.com/paper/2210.08123/) (2022)
- [Multi-View Keypoints for Reliable 6D Object Pose Estimation](https://mlsanity.com/paper/2303.16833/) (2023)
- [Active 6D Pose Estimation for Textureless Objects using Multi-View RGB Frames](https://mlsanity.com/paper/2503.03726/) (2025)
- [Structure-Aware Correspondence Learning for Relative Pose Estimation](https://mlsanity.com/paper/2503.18671/) (2025)
- [Category-Level Pose Retrieval with Contrastive Features Learnt with Occlusion Augmentation](https://mlsanity.com/paper/2208.06195/) (2022)
- [EasyVis2: A Real Time Multi-view 3D Visualization System for Laparoscopic Surgery Training Enhanced by a Deep Neural Network YOLOv8-Pose](https://mlsanity.com/paper/2412.16742/) (2024)
- [ZeroBP: Learning Position-Aware Correspondence for Zero-shot 6D Pose Estimation in Bin-Picking](https://mlsanity.com/paper/2502.01004/) (2025)
- [Adversarial samples for deep monocular 6D object pose estimation](https://mlsanity.com/paper/2203.00302/) (2022)
- [TransNet: Transparent Object Manipulation Through Category-Level Pose Estimation](https://mlsanity.com/paper/2307.12400/) (2023)
- [Instance-Adaptive Keypoint Learning with Local-to-Global Geometric Aggregation for Category-Level Object Pose Estimation](https://mlsanity.com/paper/2504.15134/) (2025)
- [Uncertainty Quantification for Visual Object Pose Estimation: S-Lemma Ellipsoidal Bounds](https://mlsanity.com/paper/2511.21666/) (2025)
- [FastPoseCNN: Real-Time Monocular Category-Level Pose and Size Estimation Framework](https://mlsanity.com/paper/2406.11063/) (2024)
- [Targeted Hard Sample Synthesis Based on Estimated Pose and Occlusion Error for Improved Object Pose Estimation](https://mlsanity.com/paper/2412.04279/) (2024)
- [Detecting Pose Estimation Failures via Keypoint Self-Consistency](https://mlsanity.com/paper/2608.03516/) (2026)
- [G6D: Geometric Learning-Free RGB-D 6D Pose Solver for Robotic Manipulation](https://mlsanity.com/paper/2609.23566/) (2026)

## Abstract (arXiv)

Accurate 6D object pose estimation is fundamental to robotic manipulation and grasping. Previous methods follow a local optimization approach which minimizes the distance between closest point pairs to handle the rotation ambiguity of symmetric objects. In this work, we propose a novel discrete-continuous formulation for rotation regression to resolve this local-optimum problem. We uniformly sample rotation anchors in SO(3), and predict a constrained deviation from each anchor to the target, as well as uncertainty scores for selecting the best prediction. Additionally, the object location is detected by aggregating point-wise vectors pointing to the 3D center. Experiments on two benchmarks: LINEMOD and YCB-Video, show that the proposed method outperforms state-of-the-art approaches. Our code is available at https://github.com/mentian/object-posenet.