mlsanityData to 7 Oct 2026

PFRL: Pose-Free Reinforcement Learning for 6D Pose Estimation

arXiv 2102.12096 ↗First posted 24 Feb 2021cs.CVcited by 14

Not on the map. Why?

Abstract (arXiv)

6D pose estimation from a single RGB image is a challenging and vital task in computer vision. The current mainstream deep model methods resort to 2D images annotated with real-world ground-truth 6D object poses, whose collection is fairly cumbersome and expensive, even unavailable in many cases. In this work, to get rid of the burden of 6D annotations, we formulate the 6D pose refinement as a Markov Decision Process and impose on the reinforcement learning approach with only 2D image annotations as weakly-supervised 6D pose information, via a delicate reward definition and a composite reinforced optimization method for efficient and effective policy training. Experiments on LINEMOD and T-LESS datasets demonstrate that our Pose-Free approach is able to achieve state-of-the-art performance compared with the methods without using real-world ground-truth 6D pose labels.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 25 of its 46 references that are in the map. First posted on arXiv 24 Feb 2021.

Builds on

25 of 46 references.

References · 25

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  3. 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,054
  4. 2018IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architecturescited by 866
  5. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 768
  6. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 721
  7. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 490
  8. 2018PVNet: Pixel-wise Voting Network for 6DoF Pose Estimationcited by 385
  9. 2018DeepIM: Deep Iterative Matching for 6D Pose Estimationcited by 283
  10. 2017SSD-6D: Making RGB-based 3D detection and 6D pose estimation great againcited by 243
  11. 2017BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depthcited by 225
  12. 2017T-LESS: An RGB-D Dataset for 6D Pose Estimation of Texture-less Objectscited by 210
13 more
  1. 2017Real-Time Seamless Single Shot 6D Object Pose Predictioncited by 210
  2. 2019DPOD: 6D Pose Object Detector and Refinercited by 189
  3. 2019Implicit 3D Orientation Learning for 6D Object Detection from RGB Imagescited by 170
  4. 2018ROI-10D: Monocular Lifting of 2D Detection to 6D Pose and Metric Shapecited by 123
  5. 20176-DoF Object Pose from Semantic Keypointscited by 89
  6. 2018Explaining the Ambiguity of Object Detection and 6D Pose From Visual Datacited by 68
  7. 2018Deep Model-Based 6D Pose Refinement in RGBcited by 59
  8. 2018StarMap for Category-Agnostic Keypoint and Viewpoint Estimationcited by 42
  9. 2018Deep Reinforcement Learning for Vision-Based Robotic Grasping: A Simulated Comparative Evaluation of Off-Policy Methodscited by 32
  10. 2017Tracking as Online Decision-Making: Learning a Policy from Streaming Videos with Reinforcement Learningcited by 14
  11. 2016PoseAgent: Budget-Constrained 6D Object Pose Estimation via Reinforcement Learningcited by 9
  12. 2019Refining 6D Object Pose Predictions using Abstract Render-and-Comparecited by 8
  13. 2019Active 6D Multi-Object Pose Estimation in Cluttered Scenarios with Deep Reinforcement Learningcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 4; 2023: 2; 2024: 1; 2025: 0; 2026: 1.

14 papers.

Sort:

  1. 2021FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimationcited by 144
  2. 2021Vote from the Center: 6 DoF Pose Estimation in RGB-D Images by Radial Keypoint Votingcited by 25
  3. 2021ReAgent: Point Cloud Registration using Imitation and Reinforcement Learningcited by 23
  4. 2023Challenges for Monocular 6D Object Pose Estimation in Roboticscited by 21
  5. 2021Reinforced Attention for Few-Shot Learning and Beyondcited by 18
  6. 2022YOLOPose: Transformer-based Multi-Object 6D Pose Estimation using Keypoint Regressioncited by 17
  7. 2021T6D-Direct: Transformers for Multi-Object 6D Pose Direct Regressioncited by 16
  8. 2022DGECN: A Depth-Guided Edge Convolutional Network for End-to-End 6D Pose Estimationcited by 12
  9. 2022A Visual Navigation Perspective for Category-Level Object Pose Estimationcited by 8
  10. 2022SporeAgent: Reinforced Scene-level Plausibility for Object Pose Refinementcited by 4
  11. 2021SynPick: A Dataset for Dynamic Bin Picking Scene Understandingcited by 3
  12. 2024CMR-Agent: Learning a Cross-Modal Agent for Iterative Image-to-Point Cloud Registrationcited by 3
2 more
  1. 2023Open Challenges for Monocular Single-shot 6D Object Pose Estimationcited by 2
  2. 2026Lucida: Parse, Generate, and Place for Composable Real-to-Sim Scene Modelingcited by 2