mlsanityData to 14 Oct 2026

Uni6Dv2: Noise Elimination for 6D Pose Estimation

arXiv 2208.06416 ↗First posted 15 Aug 2022cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Uni6D is the first 6D pose estimation approach to employ a unified backbone network to extract features from both RGB and depth images. We discover that the principal reasons of Uni6D performance limitations are Instance-Outside and Instance-Inside noise. Uni6D's simple pipeline design inherently introduces Instance-Outside noise from background pixels in the receptive field, while ignoring Instance-Inside noise in the input depth data. In this paper, we propose a two-step denoising approach for dealing with the aforementioned noise in Uni6D. To reduce noise from non-instance regions, an instance segmentation network is utilized in the first step to crop and mask the instance. A lightweight depth denoising module is proposed in the second step to calibrate the depth feature before feeding it into the pose regression network. Extensive experiments show that our Uni6Dv2 reliably and robustly eliminates noise, outperforming Uni6D without sacrificing too much inference efficiency. It also reduces the need for annotated real data that requires costly labeling.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 27 of its 39 references that are in the map. First posted on arXiv 15 Aug 2022.

Builds on

27 of 39 references.

References · 27

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2017Mask R-CNNcited by 7,277
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  4. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  5. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  6. 2015Fast R-CNNcited by 2,933
  7. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 915
  8. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 775
  9. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 724
  10. 2018PVNet: Pixel-wise Voting Network for 6DoF Pose Estimationcited by 385
  11. 2019DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusioncited by 355
  12. 2018Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objectscited by 241
15 more
  1. 2017BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depthcited by 225
  2. 2017Real-Time Seamless Single Shot 6D Object Pose Predictioncited by 210
  3. 2019PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimationcited by 204
  4. 2017PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimationcited by 170
  5. 2021GDRNPP: A Geometry-guided and Fully Learning-based Object Pose Estimatorcited by 148
  6. 2021FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimationcited by 144
  7. 2018Deep Depth Completion of a Single RGB-D Imagecited by 110
  8. 2018Segmentation-driven 6D Object Pose Estimationcited by 104
  9. 2018In Defense of Classical Image Processing: Fast Depth Completion on the CPUcited by 96
  10. 2020Self6D: Self-Supervised Monocular 6D Object Pose Estimationcited by 79
  11. 2018Making Deep Heatmaps Robust to Partial Occlusions for 3D Object Pose Estimationcited by 74
  12. 2018A Unified Framework for Multi-View Multi-Class Object Pose Estimationcited by 49
  13. 2022Uni6D: A Unified CNN Framework without Projection Breakdown for 6D Pose Estimationcited by 22
  14. 2022ES6D: A Computation Efficient and Symmetry-Aware 6D Pose Regression Frameworkcited by 19
  15. 2018SilhoNet: An RGB Method for 6D Object Pose Estimationcited by 14

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 1; 2024: 1; 2025: 1.

4 papers.

  1. 2023ZeroPose: CAD-Prompted Zero-shot Object 6D Pose Estimation in Cluttered Scenescited by 20
  2. 2024RDPN6D: Residual-based Dense Point-wise Network for 6Dof Object Pose Estimation Based on RGB-D Imagescited by 5
  3. 2022Geo6D: Geometric Constraints Learning for 6D Pose Estimationcited by 2
  4. 2025ZeroBP: Learning Position-Aware Correspondence for Zero-shot 6D Pose Estimation in Bin-Pickingcited by 2