# PyraPose: Feature Pyramids for Fast and Accurate Object Pose Estimation under Domain Shift

arXiv: https://arxiv.org/abs/2010.16117 · HTML: https://mlsanity.com/paper/2010.16117/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Oct 2020.

## Built on by (most cited first, 14 of 14)

- [ZS6D: Zero-shot 6D Object Pose Estimation using Vision Transformers](https://mlsanity.com/paper/2309.11986/) (2023)
- [Deep Learning-Based Object Pose Estimation: A Comprehensive Survey](https://mlsanity.com/paper/2405.07801/) (2024)
- [Challenges for Monocular 6D Object Pose Estimation in Robotics](https://mlsanity.com/paper/2307.12172/) (2023)
- [Sim-to-Real 6D Object Pose Estimation via Iterative Self-training for Robotic Bin Picking](https://mlsanity.com/paper/2204.07049/) (2022)
- [COPE: End-to-end trainable Constant Runtime Object Pose Estimation](https://mlsanity.com/paper/2208.08807/) (2022)
- [Self-supervised Vision Transformers for 3D Pose Estimation of Novel Objects](https://mlsanity.com/paper/2306.00129/) (2023)
- [Combining Local and Global Pose Estimation for Precise Tracking of Similar Objects](https://mlsanity.com/paper/2201.13278/) (2022)
- [YOLOPose V2: Understanding and Improving Transformer-based 6D Pose Estimation](https://mlsanity.com/paper/2307.11550/) (2023)
- [CASAPose: Class-Adaptive and Semantic-Aware Multi-Object Pose Estimation](https://mlsanity.com/paper/2210.05318/) (2022)
- [Open Challenges for Monocular Single-shot 6D Object Pose Estimation](https://mlsanity.com/paper/2302.11827/) (2023)
- [Shape-biased Texture Agnostic Representations for Improved Textureless and Metallic Object Detection and 6D Pose Estimation](https://mlsanity.com/paper/2402.04878/) (2024)
- [Grasping the Inconspicuous](https://mlsanity.com/paper/2211.08182/) (2022)
- [Modular Quantization-Aware Training for 6D Object Pose Estimation](https://mlsanity.com/paper/2303.06753/) (2023)
- [ReFlow6D: Refraction-Guided Transparent Object 6D Pose Estimation via Intermediate Representation Learning](https://mlsanity.com/paper/2412.20830/) (2024)

## Abstract (arXiv)

Object pose estimation enables robots to understand and interact with their environments. Training with synthetic data is necessary in order to adapt to novel situations. Unfortunately, pose estimation under domain shift, i.e., training on synthetic data and testing in the real world, is challenging. Deep learning-based approaches currently perform best when using encoder-decoder networks but typically do not generalize to new scenarios with different scene characteristics. We argue that patch-based approaches, instead of encoder-decoder networks, are more suited for synthetic-to-real transfer because local to global object information is better represented. To that end, we present a novel approach based on a specialized feature pyramid network to compute multi-scale features for creating pose hypotheses on different feature map resolutions in parallel. Our single-shot pose estimation approach is evaluated on multiple standard datasets and outperforms the state of the art by up to 35%. We also perform grasping experiments in the real world to demonstrate the advantage of using synthetic data to generalize to novel environments.