mlsanityData to 7 Oct 2026

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

arXiv 2311.09269 ↗First posted 15 Nov 2023cs.CV cs.AIcited by 0

Not on the map. Why?

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 26 of its 36 references that are in the map. First posted on arXiv 15 Nov 2023.

Builds on

26 of 36 references.

References · 26

  1. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  2. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 768
  3. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 490
  4. 2018PVNet: Pixel-wise Voting Network for 6DoF Pose Estimationcited by 385
  5. 2019DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusioncited by 352
  6. 2016Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networkscited by 307
  7. 2018Training Deep Networks with Synthetic Data: Bridging the Reality Gap by Domain Randomizationcited by 292
  8. 2019Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization without Accessing Target Domain Datacited by 245
  9. 2018SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloudcited by 228
  10. 2019PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimationcited by 204
  11. 2019Implicit 3D Orientation Learning for 6D Object Detection from RGB Imagescited by 170
  12. 2017An Analysis of Scale Invariance in Object Detection - SNIPcited by 119
14 more
  1. 2018Deep Depth Completion of a Single RGB-D Imagecited by 110
  2. 2020Self-Supervised Learning for Domain Adaptation on Point-Cloudscited by 99
  3. 2015Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Viewscited by 94
  4. 2018Structured Domain Randomization: Bridging the Reality Gap by Context-Aware Synthetic Datacited by 94
  5. 2014Viewpoints and Keypointscited by 59
  6. 2020ePointDA: An End-to-End Simulation-to-Real Domain Adaptation Framework for LiDAR Point Cloud Segmentationcited by 56
  7. 2022Domain Randomization-Enhanced Depth Simulation and Restoration for Perceiving and Grasping Specular and Transparent Objectscited by 49
  8. 2019Domain Adaptation for Vehicle Detection from Bird's Eye View LiDAR Point Cloud Datacited by 35
  9. 2019Large-scale 6D Object Pose Estimation Dataset for Industrial Bin-Pickingcited by 25
  10. 2021OCRTOC: A Cloud-Based Competition and Benchmark for Robotic Grasping and Manipulationcited by 24
  11. 2020Single Shot 6D Object Pose Estimationcited by 19
  12. 2016Defining the Pose of any 3D Rigid Object and an Associated Distancecited by 17
  13. 2018Symmetry Aware Evaluation of 3D Object Detection and Pose Estimation in Scenes of Many Parts in Bulkcited by 12
  14. 2023Two-Stage Grasping: A New Bin Picking Framework for Small Objectscited by 3

Built on by

Not cited yet.