mlsanityData to 7 Oct 2026

SporeAgent: Reinforced Scene-level Plausibility for Object Pose Refinement

arXiv 2201.00239 ↗First posted 1 Jan 2022cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Observational noise, inaccurate segmentation and ambiguity due to symmetry and occlusion lead to inaccurate object pose estimates. While depth- and RGB-based pose refinement approaches increase the accuracy of the resulting pose estimates, they are susceptible to ambiguity in the observation as they consider visual alignment. We propose to leverage the fact that we often observe static, rigid scenes. Thus, the objects therein need to be under physically plausible poses. We show that considering plausibility reduces ambiguity and, in consequence, allows poses to be more accurately predicted in cluttered environments. To this end, we extend a recent RL-based registration approach towards iterative refinement of object poses. Experiments on the LINEMOD and YCB-VIDEO datasets demonstrate the state-of-the-art performance of our depth-based refinement approach.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 23 of its 31 references that are in the map. First posted on arXiv 1 Jan 2022.

Builds on

23 of 31 references.

References · 23

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  3. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 768
  4. 2018Open3D: A Modern Library for 3D Data Processingcited by 717
  5. 2019DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusioncited by 352
  6. 2019Deep Closest Point: Learning Representations for Point Cloud Registrationcited by 318
  7. 2020CosyPose: Consistent multi-view multi-object 6D pose estimationcited by 287
  8. 2018DeepIM: Deep Iterative Matching for 6D Pose Estimationcited by 283
  9. 2019PointNetLK: Robust & Efficient Point Cloud Registration using PointNetcited by 231
  10. 2020Deep Global Registrationcited by 228
  11. 2017BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depthcited by 225
  12. 2017Real-Time Seamless Single Shot 6D Object Pose Predictioncited by 210
11 more
  1. 2020BOP Challenge 2020 on 6D Object Localizationcited by 192
  2. 2019DPOD: 6D Pose Object Detector and Refinercited by 189
  3. 2020RPM-Net: Robust Point Matching using Learned Featurescited by 181
  4. 2019PoseRBPF: A Rao-Blackwellized Particle Filter for 6D Object Pose Trackingcited by 91
  5. 2020DeepGMR: Learning Latent Gaussian Mixture Models for Registrationcited by 91
  6. 2020MoreFusion: Multi-object Reasoning for 6D Pose Estimation from Volumetric Fusioncited by 46
  7. 2021ReAgent: Point Cloud Registration using Imitation and Reinforcement Learningcited by 23
  8. 2020I Like to Move It: 6D Pose Estimation as an Action Decision Processcited by 22
  9. 2021PFRL: Pose-Free Reinforcement Learning for 6D Pose Estimationcited by 14
  10. 2016PoseAgent: Budget-Constrained 6D Object Pose Estimation via Reinforcement Learningcited by 9
  11. 2017Improving 6D Pose Estimation of Objects in Clutter via Physics-aware Monte Carlo Tree Searchcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 0; 2025: 0; 2026: 1.

4 papers.

  1. 2023Challenges for Monocular 6D Object Pose Estimation in Roboticscited by 21
  2. 2023Open Challenges for Monocular Single-shot 6D Object Pose Estimationcited by 2
  3. 2026Lucida: Parse, Generate, and Place for Composable Real-to-Sim Scene Modelingcited by 2
  4. 2023TrackAgent: 6D Object Tracking via Reinforcement Learningcited by 1