mlsanityData to 7 Oct 2026

MRC-Net: 6-DoF Pose Estimation with MultiScale Residual Correlation

arXiv 2403.08019 ↗First posted 12 Mar 2024cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

We propose a single-shot approach to determining 6-DoF pose of an object with available 3D computer-aided design (CAD) model from a single RGB image. Our method, dubbed MRC-Net, comprises two stages. The first performs pose classification and renders the 3D object in the classified pose. The second stage performs regression to predict fine-grained residual pose within class. Connecting the two stages is a novel multi-scale residual correlation (MRC) layer that captures high-and-low level correspondences between the input image and rendering from first stage. MRC-Net employs a Siamese network with shared weights between both stages to learn embeddings for input and rendered images. To mitigate ambiguity when predicting discrete pose class labels on symmetric objects, we use soft probabilistic labels to define pose class in the first stage. We demonstrate state-of-the-art accuracy, outperforming all competing RGB-based methods on four challenging BOP benchmark datasets: T-LESS, LM-O, YCB-V, and ITODD. Our method is non-iterative and requires no complex post-processing.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 51 of its 65 references that are in the map. First posted on arXiv 12 Mar 2024.

Builds on

51 of 65 references.

References · 51

  1. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  2. 2017Mask R-CNNcited by 7,259
  3. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  4. 2015Fast R-CNNcited by 2,930
  5. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,385
  6. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  7. 2018Group Normalizationcited by 1,514
  8. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,186
  9. 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,054
  10. 2017PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volumecited by 966
  11. 2020Accelerating 3D Deep Learning with PyTorch3Dcited by 781
  12. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 768
38 more
  1. 2020Tracking Objects as Pointscited by 483
  2. 2018PVNet: Pixel-wise Voting Network for 6DoF Pose Estimationcited by 385
  3. 2020CosyPose: Consistent multi-view multi-object 6D pose estimationcited by 287
  4. 2018DeepIM: Deep Iterative Matching for 6D Pose Estimationcited by 283
  5. 20163D Bounding Box Estimation Using Deep Learning and Geometrycited by 277
  6. 2017SSD-6D: Making RGB-based 3D detection and 6D pose estimation great againcited by 243
  7. 2022CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimationcited by 237
  8. 2017BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depthcited by 225
  9. 2019Disentangling Monocular 3D Object Detectioncited by 215
  10. 2017T-LESS: An RGB-D Dataset for 6D Pose Estimation of Texture-less Objectscited by 210
  11. 2022MegaPose: 6D Pose Estimation of Novel Objects via Render & Comparecited by 198
  12. 2020BOP Challenge 2020 on 6D Object Localizationcited by 192
  13. 2019Implicit 3D Orientation Learning for 6D Object Detection from RGB Imagescited by 170
  14. 2021GDRNPP: A Geometry-guided and Fully Learning-based Object Pose Estimatorcited by 148
  15. 2020EPOS: Estimating 6D Pose of Objects with Symmetriescited by 147
  16. 2022ZebraPose: Coarse to Fine Surface Encoding for 6DoF Object Pose Estimationcited by 115
  17. 2020HybridPose: 6D Object Pose Estimation under Hybrid Representationscited by 107
  18. 2018Segmentation-driven 6D Object Pose Estimationcited by 104
  19. 2021SurfEmb: Dense and Continuous Correspondence Distributions for Object Pose Estimation with Learnt Surface Embeddingscited by 95
  20. 2019Single-Stage 6D Object Pose Estimationcited by 88
  21. 2021SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimationcited by 88
  22. 2023EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimationcited by 79
  23. 2021RePOSE: Fast 6D Object Pose Refinement via Deep Texture Renderingcited by 63
  24. 2018Deep Model-Based 6D Pose Refinement in RGBcited by 59
  25. 2019Multi-path Learning for Object Pose Estimation Across Domainscited by 52
  26. 2022Coupled Iterative Refinement for 6D Multi-Object Pose Estimationcited by 48
  27. 2021Wide-Depth-Range 6D Object Pose Estimation in Spacecited by 45
  28. 2022RNNPose: Recurrent 6-DoF Object Pose Refinement with Robust Correspondence Field Estimation and Pose Optimizationcited by 38
  29. 2022Perspective Flow Aggregation for Data-Limited 6D Object Pose Estimationcited by 32
  30. 2022DPODv2: Dense Correspondence-Based 6 DoF Pose Estimationcited by 32
  31. 2022Neural Correspondence Field for Object Pose Estimationcited by 21
  32. 2022SC6D: Symmetry-agnostic and Correspondence-free 6D Object Pose Estimationcited by 17
  33. 2023Shape-Constraint Recurrent Flow for 6D Object Pose Estimationcited by 17
  34. 2022CRT-6D: Fast 6D Object Pose Estimation with Cascaded Refinement Transformerscited by 15
  35. 2023CheckerPose: Progressive Dense Keypoint Localization for Object Pose Estimation with Graph Neural Networkcited by 15
  36. 2023Rigidity-Aware Detection for 6D Object Pose Estimationcited by 13
  37. 2021DProST: Dynamic Projective Spatial Transformer Network for 6D Pose Estimationcited by 9
  38. 2022Knowledge Distillation for 6D Pose Estimation by Aligning Distributions of Local Predictionscited by 9

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 4; 2026: 5.

11 papers.

  1. 2024Deep Learning-Based Object Pose Estimation: A Comprehensive Surveycited by 39
  2. 2025V-HOP: Visuo-Haptic 6D Object Pose Trackingcited by 4
  3. 2024BOP-Distrib: Revisiting 6D Pose Estimation Benchmarks for Better Evaluation under Visual Ambiguitiescited by 3
  4. 2025ViTa-Zero: Zero-shot Visuotactile Object 6D Pose Estimationcited by 3
  5. 2025Zero-shot Inexact CAD Model Alignment from a Single Imagecited by 1
  6. 2026Cov2Pose: Leveraging Spatial Covariance for Direct Manifold-aware 6-DoF Object Pose Estimationcited by 1
  7. 2026Towards Symmetry-sensitive Pose Estimation: A Rotation Representation for Symmetric Object Classescited by 1
  8. 2025RAG-6DPose: Retrieval-Augmented 6D Pose Estimation via Leveraging CAD as Knowledge Basecited by 0
  9. 2026Yolo-Key-6D: Single Stage Monocular 6D Pose Estimation with Keypoint Enhancementscited by 0
  10. 2026SurfSurg6D: Geometry Consistent Dense Correspondence for Textureless Surgical Instrument Pose Estimationcited by 0
  11. 2026GAP-GDRNet: Geometry-aware monocular 6D pose estimation for spacecraft using synthetic geometric supervisioncited by 0