mlsanityData to 7 Oct 2026

MV6D: Multi-View 6D Pose Estimation on RGB-D Frames Using a Deep Point-wise Voting Network

arXiv 2208.01172 ↗First posted 1 Aug 2022cs.CV cs.AI cs.LGcited by 9

Not on the map. Why?

Abstract (arXiv)

Estimating 6D poses of objects is an essential computer vision task. However, most conventional approaches rely on camera data from a single perspective and therefore suffer from occlusions. We overcome this issue with our novel multi-view 6D pose estimation method called MV6D which accurately predicts the 6D poses of all objects in a cluttered scene based on RGB-D images from multiple perspectives. We base our approach on the PVN3D network that uses a single RGB-D image to predict keypoints of the target objects. We extend this approach by using a combined point cloud from multiple views and fusing the images from each view with a DenseFusion layer. In contrast to current multi-view pose detection networks such as CosyPose, our MV6D can learn the fusion of multiple perspectives in an end-to-end manner and does not require multiple prediction stages or subsequent fine tuning of the prediction. Furthermore, we present three novel photorealistic datasets of cluttered scenes with heavy occlusions. All of them contain RGB-D images from multiple perspectives and the ground truth for instance semantic segmentation and 6D pose estimation. MV6D significantly outperforms the state-of-the-art in multi-view 6D pose estimation even in cases where the camera poses are known inaccurately. Furthermore, we show that our approach is robust towards dynamic camera setups and that its accuracy increases incrementally with an increasing number of perspectives.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 32 of its 65 references that are in the map. First posted on arXiv 1 Aug 2022.

Builds on

32 of 65 references.

References · 32

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  5. 2016Pyramid Scene Parsing Networkcited by 2,472
  6. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  7. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  8. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 768
  9. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 721
  10. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  11. 2015Cyclical Learning Rates for Training Neural Networkscited by 627
  12. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
20 more
  1. 2018PVNet: Pixel-wise Voting Network for 6DoF Pose Estimationcited by 385
  2. 2019DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusioncited by 352
  3. 2017Joint 3D Proposal Generation and Object Detection from View Aggregationcited by 325
  4. 2020CosyPose: Consistent multi-view multi-object 6D pose estimationcited by 287
  5. 2018DeepIM: Deep Iterative Matching for 6D Pose Estimationcited by 283
  6. 2017SSD-6D: Making RGB-based 3D detection and 6D pose estimation great againcited by 243
  7. 2017T-LESS: An RGB-D Dataset for 6D Pose Estimation of Texture-less Objectscited by 210
  8. 2017Real-Time Seamless Single Shot 6D Object Pose Predictioncited by 210
  9. 2019PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimationcited by 204
  10. 2019DPOD: 6D Pose Object Detector and Refinercited by 189
  11. 2017PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimationcited by 170
  12. 2019Implicit 3D Orientation Learning for 6D Object Detection from RGB Imagescited by 170
  13. 2021FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimationcited by 144
  14. 2015Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Viewscited by 94
  15. 20176-DoF Object Pose from Semantic Keypointscited by 89
  16. 2016Multi-view Self-supervised Deep Learning for 6D Pose Estimation in the Amazon Picking Challengecited by 70
  17. 2014Viewpoints and Keypointscited by 59
  18. 20163D Fully Convolutional Network for Vehicle Detection in Point Cloudcited by 57
  19. 2018A Unified Framework for Multi-View Multi-Class Object Pose Estimationcited by 49
  20. 2019CullNet: Calibrated and Pose Aware Confidence Scores for Object Pose Estimationcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 1; 2024: 3; 2025: 3; 2026: 1.

9 papers.

  1. 2024Instance-Adaptive and Geometric-Aware Keypoint Learning for Category-Level 6D Object Pose Estimationcited by 41
  2. 2024Deep Learning-Based Object Pose Estimation: A Comprehensive Surveycited by 39
  3. 2022Multi-view object pose estimation from correspondence distributions and epipolar geometrycited by 5
  4. 2023SyMFM6D: Symmetry-aware Multi-directional Fusion for Multi-View 6D Object Pose Estimationcited by 4
  5. 2024A Low-Cost, High-Speed, and Robust Bin Picking System for Factory Automation Enabled by a Non-Stop, Multi-View, and Active Vision Schemecited by 2
  6. 2026MultiCam: On-the-fly Multi-Camera Pose Estimation Using Spatiotemporal Overlaps of Known Objectscited by 1
  7. 20256D Pose Estimation on Point Cloud Data through Prior Knowledge Integration: A Case Study in Autonomous Disassemblycited by 0
  8. 2025MVTOP: Multi-View Transformer-based Object Pose-Estimationcited by 0
  9. 2025SDT-6D: Fully Sparse Depth-Transformer for Staged End-to-End 6D Pose Estimation in Industrial Multi-View Bin Pickingcited by 0