# NormNet: Scale Normalization for 6D Pose Estimation in Stacked Scenarios

arXiv: https://arxiv.org/abs/2311.09269 · HTML: https://mlsanity.com/paper/2311.09269/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 36 references that are in the map.
- First posted on arXiv 15 Nov 2023.

## Builds on (most cited first, 26 of 26)

- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes](https://mlsanity.com/paper/1711.00199/) (2017)
- [Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation](https://mlsanity.com/paper/1901.02970/) (2019)
- [PVNet: Pixel-wise Voting Network for 6DoF Pose Estimation](https://mlsanity.com/paper/1812.11788/) (2018)
- [DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion](https://mlsanity.com/paper/1901.04780/) (2019)
- [Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks](https://mlsanity.com/paper/1612.05424/) (2016)
- [Training Deep Networks with Synthetic Data: Bridging the Reality Gap by Domain Randomization](https://mlsanity.com/paper/1804.06516/) (2018)
- [Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization without Accessing Target Domain Data](https://mlsanity.com/paper/1909.00889/) (2019)
- [SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud](https://mlsanity.com/paper/1809.08495/) (2018)
- [PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimation](https://mlsanity.com/paper/1911.04231/) (2019)
- [Implicit 3D Orientation Learning for 6D Object Detection from RGB Images](https://mlsanity.com/paper/1902.01275/) (2019)
- [An Analysis of Scale Invariance in Object Detection - SNIP](https://mlsanity.com/paper/1711.08189/) (2017)
- [Deep Depth Completion of a Single RGB-D Image](https://mlsanity.com/paper/1803.09326/) (2018)
- [Self-Supervised Learning for Domain Adaptation on Point-Clouds](https://mlsanity.com/paper/2003.12641/) (2020)
- [Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Views](https://mlsanity.com/paper/1505.05641/) (2015)
- [Structured Domain Randomization: Bridging the Reality Gap by Context-Aware Synthetic Data](https://mlsanity.com/paper/1810.10093/) (2018)
- [Viewpoints and Keypoints](https://mlsanity.com/paper/1411.6067/) (2014)
- [ePointDA: An End-to-End Simulation-to-Real Domain Adaptation Framework for LiDAR Point Cloud Segmentation](https://mlsanity.com/paper/2009.03456/) (2020)
- [Domain Randomization-Enhanced Depth Simulation and Restoration for Perceiving and Grasping Specular and Transparent Objects](https://mlsanity.com/paper/2208.03792/) (2022)
- [Domain Adaptation for Vehicle Detection from Bird's Eye View LiDAR Point Cloud Data](https://mlsanity.com/paper/1905.08955/) (2019)
- [Large-scale 6D Object Pose Estimation Dataset for Industrial Bin-Picking](https://mlsanity.com/paper/1912.12125/) (2019)
- [OCRTOC: A Cloud-Based Competition and Benchmark for Robotic Grasping and Manipulation](https://mlsanity.com/paper/2104.11446/) (2021)
- [Single Shot 6D Object Pose Estimation](https://mlsanity.com/paper/2004.12729/) (2020)
- [Defining the Pose of any 3D Rigid Object and an Associated Distance](https://mlsanity.com/paper/1612.04631/) (2016)
- [Symmetry Aware Evaluation of 3D Object Detection and Pose Estimation in Scenes of Many Parts in Bulk](https://mlsanity.com/paper/1806.08129/) (2018)
- [Two-Stage Grasping: A New Bin Picking Framework for Small Objects](https://mlsanity.com/paper/2303.02604/) (2023)

## Abstract (arXiv)

Existing Object Pose Estimation (OPE) methods for stacked scenarios are not robust to changes in object scale. This paper proposes a new 6DoF OPE network (NormNet) for different scale objects in stacked scenarios. Specifically, each object's scale is first learned with point-wise regression. Then, all objects in the stacked scenario are normalized into the same scale through semantic segmentation and affine transformation. Finally, they are fed into a shared pose estimator to recover their 6D poses. In addition, we introduce a new Sim-to-Real transfer pipeline, combining style transfer and domain randomization. This improves the NormNet's performance on real data even if we only train it on synthetic data. Extensive experiments demonstrate that the proposed method achieves state-of-the-art performance on public benchmarks and the MultiScale dataset we constructed. The real-world experiments show that our method can robustly estimate the 6D pose of objects at different scales.